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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ennessee
    -0.07
     články
    -0.06
     Pra
    -0.06
     timeless
    -0.06
     Employ
    -0.06
     distilled
    -0.06
    |min
    -0.06
     explosives
    -0.06
     غربی
    -0.06
     notorious
    -0.06
    POSITIVE LOGITS
    Enumerable
    0.08
    Attribute
    0.06
    terms
    0.06
    .invoke
    0.06
    veral
    0.06
    ELEMENT
    0.06
     Savage
    0.06
    _exact
    0.06
    (ci
    0.06
    //
    0.06
    Act Density 0.062%

    No Known Activations