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

    Neuronpedia

    INDEX
    Explanations

    punctuation and certain types of contractions or possessive forms

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

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.47
     betweenstory
    -0.44
     practical
    -0.35
    arangay
    -0.35
    verhältnisse
    -0.34
    BG
    -0.34
    asyarakat
    -0.34
     walk
    -0.34
    ArgsConstructor
    -0.33
    回戦
    -0.32
    POSITIVE LOGITS
     Audiodateien
    0.59
    oneofs
    0.58
    WritableDatabase
    0.57
    ViewImports
    0.57
    LookAnd
    0.55
     NavController
    0.53
    EDEFAULT
    0.53
     transfieras
    0.52
     Paglinawan
    0.51
    openqa
    0.50
    Act Density 0.002%

    No Known Activations