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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ویرایش
    -0.07
    “But
    -0.07
    开放
    -0.06
     адже
    -0.06
     редак
    -0.06
     graf
    -0.06
    帰
    -0.06
     baff
    -0.06
     прог
    -0.06
    .od
    -0.06
    POSITIVE LOGITS
    ソン
    0.08
    _voice
    0.07
     complication
    0.06
    el
    0.06
    ecies
    0.06
     Taipei
    0.06
    EMY
    0.06
    /delete
    0.06
    ulos
    0.06
    /></
    0.06
    Act Density 0.010%

    No Known Activations