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

    Neuronpedia

    INDEX
    Explanations

    Quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فع
    -0.07
     undoubtedly
    -0.06
    ��
    -0.06
    еров
    -0.06
     �
    -0.06
    �
    -0.06
     Shen
    -0.06
    τώ
    -0.06
    lum
    -0.06
     Independence
    -0.06
    POSITIVE LOGITS
    exampleInput
    0.07
     rms
    0.06
     Little
    0.06
     �
    0.06
     malformed
    0.06
     shrimp
    0.06
    educated
    0.06
    .normalize
    0.06
     Biological
    0.06
    getInt
    0.06
    Act Density 0.001%

    No Known Activations