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

    Neuronpedia

    INDEX
    Explanations

    characters or symbols that indicate transitions or prepositions

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

    prefix "pre" or "fore"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    asteroide
    -0.48
    TagMode
    -0.47
    Spoljašnje
    -0.46
    Hentet
    -0.46
    pantalón
    -0.46
    chaleco
    -0.45
     nahilalakip
    -0.44
     aikaa
    -0.44
    cerely
    -0.42
    kurtka
    -0.41
    POSITIVE LOGITS
     Пред
    0.55
    Пред
    0.55
     Pref
    0.54
     Pron
    0.50
     pré
    0.50
     пред
    0.49
    Προ
    0.48
    beforeEach
    0.48
     Pred
    0.46
     pref
    0.46
    Act Density 0.002%

    No Known Activations