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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ẵ
    -0.07
     rats
    -0.07
    トリ
    -0.07
    خذ
    -0.07
    先生
    -0.07
     وال
    -0.06
     plac
    -0.06
     застосування
    -0.06
     sidelines
    -0.06
    经营
    -0.06
    POSITIVE LOGITS
    /')
    0.07
    струмент
    0.06
    Method
    0.06
    스는
    0.06
    --[[
    0.06
    수를
    0.06
    });↵↵↵
    0.06
    oystick
    0.06
    "default
    0.06
    (lo
    0.05
    Act Density 0.152%

    No Known Activations