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

    Neuronpedia

    INDEX
    Explanations

    declarations and definitions of constants and variables in programming code

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

    mathematical constants and code definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awaiter
    -0.42
    RegressionTest
    -0.41
    وصلات
    -0.41
     esternos
    -0.40
    ScopeManager
    -0.39
     isSet
    -0.38
    הערות
    -0.37
     CURIAM
    -0.37
    ätzlich
    -0.36
     NAR
    -0.36
    POSITIVE LOGITS
     transfieras
    0.48
    awtextra
    0.47
     maxn
    0.47
    onias
    0.46
     gynhyrchwyd
    0.45
    TypedDataSet
    0.44
    tissa
    0.44
    Werdegang
    0.43
    AutoScaleMode
    0.43
    tinyos
    0.43
    Act Density 0.005%

    No Known Activations