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

    Neuronpedia

    INDEX
    Explanations

    story descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Of
    -0.07
     l�
    -0.06
    яз
    -0.06
     revelations
    -0.06
    ्पन
    -0.06
    _black
    -0.06
    Total
    -0.06
    cuda
    -0.06
     comida
    -0.06
    İTESİ
    -0.06
    POSITIVE LOGITS
     Moderate
    0.07
    設
    0.06
     JOIN
    0.06
    lator
    0.06
    阶
    0.06
    atives
    0.06
     привед
    0.06
    ازند
    0.06
     клу
    0.06
     xúc
    0.06
    Act Density 0.031%

    No Known Activations