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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and method calls associated with object manipulation

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

    method calls with colons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ">//
    -0.44
    ngOnInit
    -0.34
    /
    -0.34
     (
    -0.31
    /-
    -0.30
    か
    -0.29
     kind
    -0.29
    lorus
    -0.29
    +
    -0.29
    ->__
    -0.29
    POSITIVE LOGITS
     nghiệm
    2.19
     isEqualToString
    1.08
     nghiệ
    0.89
    intValue
    0.88
     objectAtIndex
    0.81
    ệm
    0.80
     clearColor
    0.75
     intValue
    0.75
     stringBy
    0.75
     nghiệp
    0.73
    Act Density 0.002%

    No Known Activations