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

    Neuronpedia

    INDEX
    Explanations

    your mind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kancel
    0.73
    emu
    0.71
    聲音
    0.69
    )}^{
    0.69
     dubbio
    0.67
     Rooms
    0.66
    zyloxy
    0.66
     وضعیت
    0.65
     ஆண்டுகள்
    0.65
     حضور
    0.64
    POSITIVE LOGITS
     behalf
    1.92
     basis
    1.73
     وعلى
    1.63
    basis
    1.60
     occasions
    1.51
    Basis
    1.41
     occasion
    1.39
     sidelines
    1.34
     Basis
    1.25
     grounds
    1.24
    Act Density 0.229%

    No Known Activations