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

    Neuronpedia

    INDEX
    Explanations

    symbols and notations typically used in programming or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    user license

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.54
    Slf
    -0.51
    AutoField
    -0.50
    ReusableCell
    -0.48
    openid
    -0.48
    providedIn
    -0.47
    XmlAccessType
    -0.47
    contentLoaded
    -0.45
    GenerationType
    -0.42
    tagext
    -0.41
    POSITIVE LOGITS
    ValueStyle
    0.52
    Einzelnachweise
    0.51
    $_['
    0.46
    versies
    0.45
    ouncements
    0.45
    ◞
    0.43
    ometra
    0.43
    tisseur
    0.41
    ConstraintMaker
    0.41
    Портали
    0.40
    Act Density 0.000%

    No Known Activations