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

    Neuronpedia

    INDEX
    Explanations

    references to configuration settings or preferences in a system

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

    preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RotationOrder
    -0.59
    enterOuterAlt
    -0.57
    jsonwebtoken
    -0.56
    ISupport
    -0.52
    WEBPACK
    -0.51
    AxisAlignment
    -0.48
    ExtendWith
    -0.46
    DebuggerStep
    -0.46
     MainAxisSize
    -0.46
     arşivlendi
    -0.45
    POSITIVE LOGITS
    Preference
    1.02
    preference
    0.91
     Preference
    0.79
     preference
    0.73
    IntoConstraints
    0.53
     HFILL
    0.52
    Preferences
    0.51
     ligiloj
    0.51
     préférence
    0.51
    Enllaços
    0.48
    Act Density 0.003%

    No Known Activations