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

    Neuronpedia

    INDEX
    Explanations

    function definition (def)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    217
    -0.08
     труб
    -0.07
     Kurum
    -0.07
     forfeiture
    -0.07
    693
    -0.06
     hudeb
    -0.06
     chol
    -0.06
    TeV
    -0.06
     enthusi
    -0.06
     timeZone
    -0.06
    POSITIVE LOGITS
     altered
    0.07
    ерше
    0.07
    ル
    0.07
    (plot
    0.06
     raises
    0.06
    _DEBUG
    0.06
    сте
    0.06
    ाड
    0.06
     ون
    0.06
    .pref
    0.06
    Act Density 0.028%

    No Known Activations