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

    Neuronpedia

    INDEX
    Explanations

    HTTP response codes

    oai_token-act-pair · gemini-2.0-flash

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    httphttps
    -0.70
    XmlAccessType
    -0.60
     охо
    -0.54
    atak
    -0.52
    🥞
    -0.51
     cul
    -0.50
    LookAnd
    -0.50
    forschung
    -0.49
    iorna
    -0.49
    endregion
    -0.49
    POSITIVE LOGITS
    #+#
    0.94
     EClass
    0.57
    IntoConstraints
    0.56
    buttonBar
    0.56
     Италијани
    0.52
     AAS
    0.51
    rizona
    0.51
    EDEFAULT
    0.50
     ADI
    0.50
    ựng
    0.48
    Act Density 0.483%

    No Known Activations