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

    Neuronpedia

    INDEX
    Explanations

    adding or subtracting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .UTC
    -0.07
    -horizontal
    -0.06
    Suc
    -0.06
    Al
    -0.06
    Gap
    -0.06
    ミュ
    -0.06
    .money
    -0.06
    _lista
    -0.06
     Ara
    -0.06
    inidad
    -0.06
    POSITIVE LOGITS
    電視
    0.07
    .UTF
    0.06
     compatible
    0.06
     Endpoint
    0.06
     Ford
    0.06
    _checkpoint
    0.06
    營
    0.06
     ремонт
    0.06
    UserName
    0.06
     จำก
    0.06
    Act Density 0.040%

    No Known Activations