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

    Neuronpedia

    INDEX
    Explanations

    inequalities and values

    oai_token-act-pair · gemini-2.0-flash

    Comparisons and measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.79
    LookAnd
    -0.60
    MessageTagHelper
    -0.55
    spaceBetween
    -0.52
    IVEREF
    -0.50
    Jegyzetek
    -0.47
    featureID
    -0.45
    lacht
    -0.45
    amment
    -0.44
     divertimento
    -0.44
    POSITIVE LOGITS
    <bos>
    0.73
     AssemblyCompany
    0.64
     ThemeData
    0.60
    ="@+
    0.54
     couv
    0.53
    ">//
    0.53
     الاطلاع
    0.52
    ***********/
    0.52
    اقرأ
    0.52
    newtheorem
    0.51
    Act Density 1.819%

    No Known Activations