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

    Neuronpedia

    INDEX
    Explanations

    poster

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __('
    -0.06
    anic
    -0.06
     �
    -0.06
    .nasa
    -0.06
     обов
    -0.06
    _yes
    -0.06
     Islamabad
    -0.06
     Kushner
    -0.06
    121
    -0.06
    ـ
    -0.06
    POSITIVE LOGITS
    MODE
    0.07
     가까
    0.07
    Attrib
    0.07
     Training
    0.07
    一下
    0.06
     یکی
    0.06
    考试
    0.06
     #$
    0.06
    WG
    0.06
     Hmm
    0.06
    Act Density 0.000%

    No Known Activations