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

    Neuronpedia

    INDEX
    Explanations

    running flask code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xmax
    0.70
    ."))
    0.66
     participants
    0.65
     സംസ്
    0.65
    ocor
    0.64
     coron
    0.64
     Cec
    0.63
    Participants
    0.63
     Suz
    0.62
    ચ્છ
    0.62
    POSITIVE LOGITS
    考虑
    0.71
    做好
    0.67
     발
    0.67
     অনুপ
    0.66
     branded
    0.65
     näher
    0.64
     रामानंद
    0.64
     Unlock
    0.64
    branded
    0.63
     incum
    0.63
    Act Density 0.006%

    No Known Activations