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

    Neuronpedia

    INDEX
    Explanations

    numpy python code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shortlist
    0.77
    mathcal
    0.74
    UK
    0.72
    }}_
    0.72
     Landmark
    0.71
     новой
    0.69
    sub
    0.69
    ƌ
    0.69
     Library
    0.68
    पाद
    0.68
    POSITIVE LOGITS
    .-\
    0.70
     affirmative
    0.69
     threes
    0.69
     thirty
    0.67
     commer
    0.67
     douze
    0.67
    囯
    0.67
     interiores
    0.66
    ேசு
    0.65
    ército
    0.65
    Act Density 0.003%

    No Known Activations