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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     widening
    -0.07
     vomiting
    -0.06
    itures
    -0.06
     PMC
    -0.06
    imized
    -0.06
    Mill
    -0.06
    prepared
    -0.06
    ného
    -0.06
     Patton
    -0.06
    ILogger
    -0.06
    POSITIVE LOGITS
     decimal
    0.08
     ışık
    0.07
     Β
    0.07
     неболь
    0.07
     misunderstood
    0.06
     IconData
    0.06
     تصم
    0.06
     xung
    0.06
     알
    0.06
    状态
    0.06
    Act Density 0.003%

    No Known Activations