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

    Neuronpedia

    INDEX
    Explanations

    insults and jokes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     잔
    -0.07
    _thr
    -0.06
    çesi
    -0.06
     stronghold
    -0.06
    งช
    -0.06
    ่าค
    -0.06
    เคล
    -0.06
    ереж
    -0.06
     توم
    -0.06
    束
    -0.06
    POSITIVE LOGITS
    ;?></
    0.07
    _CALLBACK
    0.07
     Vor
    0.07
     Unlock
    0.07
    Tube
    0.06
     Obesity
    0.06
    History
    0.06
     vua
    0.06
    ?.
    0.06
    ında
    0.06
    Act Density 0.004%

    No Known Activations