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

    Neuronpedia

    INDEX
    Explanations

    occurrences of opening curly braces in code

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

    Java access modifiers (private, public, protected)

    np_acts-logits-general · gemini-2.0-flash

    programming access modifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.64
    jsonwebtoken
    -0.60
    aarrggbb
    -0.58
     ModelExpression
    -0.56
    latego
    -0.54
    tern
    -0.53
    audiovisuel
    -0.53
    IsMutable
    -0.53
    lach
    -0.52
    kuuta
    -0.52
    POSITIVE LOGITS
    private
    0.72
     private
    0.69
    __":
    0.62
     public
    0.60
    __':
    0.59
     privée
    0.57
    public
    0.56
    InjectAttribute
    0.56
    ↵
    0.54
    protected
    0.53
    Act Density 0.022%

    No Known Activations