Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    transitions and changes in personal circumstances or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding specific punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    technical terms and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CharacterOffset
    -0.63
     незавершена
    -0.53
     विश्वसनीयता
    -0.47
    Bibliograf
    -0.47
    Kaynakça
    -0.44
    Vidite
    -0.43
    Referanser
    -0.43
     linkovi
    -0.41
    اریخ
    -0.41
    Datuak
    -0.39
    POSITIVE LOGITS
    IBOutlet
    0.49
     GenerationType
    0.46
     ब्रेकडाउन
    0.44
     EconPapers
    0.42
    bootstrapcdn
    0.41
    enderror
    0.39
    ContentAlignment
    0.39
     lég
    0.38
     setAddress
    0.38
    ArgsConstructor
    0.38
    Act Density 0.547%

    No Known Activations