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

    Neuronpedia

    INDEX
    Explanations

    Calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _delegate
    -0.07
     "$
    -0.07
     phrase
    -0.07
     Commerce
    -0.07
    sometimes
    -0.07
    tg
    -0.06
    Curso
    -0.06
     elseif
    -0.06
     sonuç
    -0.06
    (dev
    -0.06
    POSITIVE LOGITS
    .textLabel
    0.07
    كيب
    0.07
     valuation
    0.07
    _
↵
↵
    0.06
    _;↵
    0.06
    .Names
    0.06
    _-
    0.06
     satış
    0.06
     patri
    0.06
    핑
    0.06
    Act Density 0.006%

    No Known Activations