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

    Neuronpedia

    INDEX
    Explanations

    code of conduct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ender
    0.97
    ans
    0.86
    интере
    0.84
    AD
    0.83
    END
    0.83
    ant
    0.81
    response
    0.81
    ac
    0.80
    unless
    0.79
    ſe
    0.79
    POSITIVE LOGITS
    ൂര്‍
    0.75
     embezzlement
    0.73
    𝐒
    0.73
     Sd
    0.72
     Vander
    0.71
     Jumat
    0.71
     embezz
    0.71
     Sanit
    0.71
     atrophy
    0.70
     eril
    0.70
    Act Density 0.001%

    No Known Activations