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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conject
    -0.06
     harming
    -0.06
     QApplication
    -0.06
    ゝ
    -0.06
    (fc
    -0.06
    .stock
    -0.06
    _recent
    -0.06
    jar
    -0.06
     array
    -0.06
    $/,↵
    -0.06
    POSITIVE LOGITS
    gow
    0.07
    eking
    0.06
     Marseille
    0.06
    _frag
    0.06
    μιο
    0.06
    etSocketAddress
    0.06
    ظٹط
    0.06
     киш
    0.06
     har
    0.06
     configur
    0.06
    Act Density 0.206%

    No Known Activations