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

    Neuronpedia

    INDEX
    Explanations

    "===="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ump
    -0.08
     Pole
    -0.08
    cale
    -0.07
     light
    -0.07
     moisture
    -0.07
    SetValue
    -0.07
     Light
    -0.07
    -light
    -0.07
    Ein
    -0.07
    лит
    -0.07
    POSITIVE LOGITS
    --------------------------------
    0.09
    /********************************
    0.08
    ================================
    0.08
     queued
    0.08
     --------------------------------
    0.07
     hissed
    0.07
    .instagram
    0.07
    ("--------------------------------
    0.07
    棚
    0.07
    Johnny
    0.07
    Act Density 0.003%

    No Known Activations