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

    Neuronpedia

    INDEX
    Explanations

    them

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Thinking
    -0.07
    ker
    -0.07
     radios
    -0.06
     秋
    -0.06
    ربی
    -0.06
    (Layout
    -0.06
    zv
    -0.06
    My
    -0.06
    Guide
    -0.06
     kötü
    -0.06
    POSITIVE LOGITS
    .extract
    0.07
    _format
    0.07
    .Event
    0.07
    .band
    0.07
     burial
    0.07
    .alignment
    0.06
     union
    0.06
    [src
    0.06
     congreg
    0.06
     connexion
    0.06
    Act Density 0.208%

    No Known Activations