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

    Neuronpedia

    INDEX
    Explanations

    numeric values associated with specific metrics or measurements

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

    dois ponto barra

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forState
    -0.42
     doInBackground
    -0.40
    czu
    -0.36
     annonces
    -0.36
     sûre
    -0.35
    camisas
    -0.34
    NewLabel
    -0.34
    stdarg
    -0.33
    dasarkan
    -0.32
     açıklama
    -0.32
    POSITIVE LOGITS
    RegressionTest
    0.75
    FunctionFlags
    0.66
     otomatig
    0.65
    ScopeManager
    0.58
    uxxxx
    0.55
    RectangleBorder
    0.54
    NameInMap
    0.53
     препратки
    0.53
    SPATH
    0.53
    SequentialGroup
    0.52
    Act Density 0.148%

    No Known Activations