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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     predictors
    -0.08
    chester
    -0.07
    -six
    -0.07
    block
    -0.07
    ça
    -0.06
     Democracy
    -0.06
    _heads
    -0.06
    architecture
    -0.06
    dots
    -0.06
    preci
    -0.06
    POSITIVE LOGITS
     quaint
    0.07
     ');
    0.07
    Preview
    0.06
    ":{↵
    0.06
     shimmer
    0.06
    EP
    0.06
     JVM
    0.06
    velope
    0.06
    .radio
    0.06
     ชนะ
    0.06
    Act Density 0.001%

    No Known Activations