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

    Neuronpedia

    INDEX
    Explanations

    city in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    гүй
    0.96
    ิน
    0.95
    י
    0.93
    siniz
    0.93
     Voici
    0.89
    us
    0.86
     vary
    0.85
    ل
    0.85
    ม
    0.84
    tumblr
    0.84
    POSITIVE LOGITS
     imaginable
    1.04
     of
    0.91
     that
    0.88
    Ме
    0.88
     यही
    0.81
    міна
    0.80
    Ре
    0.79
    <unused742>
    0.78
     commemorating
    0.76
    хода
    0.75
    Act Density 0.409%

    No Known Activations