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

    Neuronpedia

    INDEX
    Explanations

    List markers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (desc
    -0.06
     Eva
    -0.06
     conspir
    -0.06
     Homer
    -0.06
    HONE
    -0.06
    苹果
    -0.06
    Failed
    -0.06
    .getLog
    -0.06
    ει
    -0.06
    .frames
    -0.06
    POSITIVE LOGITS
    :L
    0.07
     автомати
    0.06
    .mul
    0.06
    '$
    0.06
    이크
    0.06
    otherwise
    0.06
    (ele
    0.06
    IRECTION
    0.06
    imageUrl
    0.06
    CG
    0.06
    Act Density 0.019%

    No Known Activations