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

    Neuronpedia

    INDEX
    Explanations

    model weights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     formulaire
    -0.06
    -self
    -0.06
     PROF
    -0.06
     corpses
    -0.06
     makeover
    -0.06
    _answers
    -0.06
    以后
    -0.06
     Май
    -0.06
    _values
    -0.06
     مور
    -0.06
    POSITIVE LOGITS
    ROADCAST
    0.07
    ียร
    0.07
     closely
    0.06
    accepted
    0.06
     targeting
    0.06
    UTES
    0.06
     fifty
    0.06
    :::::::
    0.06
     credited
    0.06
    先
    0.06
    Act Density 0.003%

    No Known Activations