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

    Neuronpedia

    INDEX
    Explanations

    code structures and syntax related to programming

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

    programming code annotations and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.37
     للمعارف
    -0.34
    intenant
    -0.31
     Wol
    -0.29
     TestBed
    -0.29
    idenav
    -0.29
     Uniwers
    -0.29
    ứ
    -0.28
    deutung
    -0.28
     kohdetta
    -0.28
    POSITIVE LOGITS
    UIControlState
    0.65
    πομπ
    0.52
    tershire
    0.51
    AnchorStyles
    0.50
     useCallback
    0.50
    chappement
    0.49
    majánló
    0.48
    DebuggerNonUser
    0.47
    XmlElement
    0.47
    ⃤
    0.47
    Act Density 0.000%

    No Known Activations