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

    Neuronpedia

    INDEX
    Explanations

    random text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dị
    -0.07
     cancer
    -0.06
    Calcul
    -0.06
     disrespect
    -0.06
    ��
    -0.06
     nuclei
    -0.06
     dictionary
    -0.06
    _histogram
    -0.06
     polit
    -0.06
    δί
    -0.06
    POSITIVE LOGITS
    ('('
    0.07
    ประช
    0.07
    (move
    0.07
    善
    0.06
    lanma
    0.06
    Force
    0.06
    拟
    0.06
    ，這
    0.06
     Bliss
    0.06
    hoff
    0.06
    Act Density 0.000%

    No Known Activations