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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .jar
    -0.07
    औ
    -0.07
     मर
    -0.06
    Cc
    -0.06
    .analysis
    -0.06
    挂
    -0.06
     σύ
    -0.06
    .ID
    -0.06
     WhatsApp
    -0.06
    มาก
    -0.06
    POSITIVE LOGITS
     pointing
    0.07
    ã
    0.06
     BIO
    0.06
     Gore
    0.06
    (string
    0.06
    ından
    0.06
    aidu
    0.06
     Moh
    0.06
    IBOutlet
    0.06
    arking
    0.06
    Act Density 0.039%

    No Known Activations