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

    Neuronpedia

    INDEX
    Explanations

    Stuff Queer People

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hiers
    -0.84
     moletom
    -0.79
    无疑
    -0.77
    ឆ
    -0.76
     Woh
    -0.76
    toc
    -0.75
     NRC
    -0.74
     provin
    -0.74
     perca
    -0.74
     преиму
    -0.74
    POSITIVE LOGITS
     Vulture
    0.98
     Reg
    0.94
     ®
    0.87
    reg
    0.84
    Reg
    0.78
    ercicio
    0.77
    Sponsored
    0.75
     silicon
    0.71
     SFR
    0.70
     µ
    0.70
    Act Density 0.046%

    No Known Activations