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

    Neuronpedia

    INDEX
    Explanations

    My whiskers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    オリ
    0.75
     storey
    0.65
     drugstore
    0.65
    0.64
    đen
    0.64
    0.64
     crowds
    0.63
     premières
    0.63
    ěj
    0.63
     payoffs
    0.62
    POSITIVE LOGITS
     ngươi
    0.98
     rayos
    0.98
    !!!
    0.94
    eeee
    0.94
     ইহা
    0.93
    aaaaaaaa
    0.93
    yyyyyyyy
    0.92
    !!!!!!
    0.92
    욧
    0.92
    !!!!!!!!
    0.91
    Act Density 0.340%

    No Known Activations