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

    Neuronpedia

    INDEX
    Explanations

    code, documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    買って
    -0.08
     Billion
    -0.07
    椹
    -0.07
    🍫
    -0.07
    :A
    -0.07
     الكمبي
    -0.07
     hurry
    -0.07
     Adaptive
    -0.07
    𝘫
    -0.07
    ℃
    -0.06
    POSITIVE LOGITS
    lat
    0.07
    .SYSTEM
    0.07
    belie
    0.07
     ego
    0.07
    Mayor
    0.07
    無法
    0.07
    _coords
    0.07
     skeptic
    0.06
    -font
    0.06
     stagger
    0.06
    Act Density 0.024%

    No Known Activations