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

    Neuronpedia

    INDEX
    Explanations

    instances of high numerical values and references to significance or importance

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

    programming and legal contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    [toxicity=0]
    -0.57
     Krug
    -0.47
     Speer
    -0.46
     Erbe
    -0.45
     Huerta
    -0.45
    Assertions
    -0.43
     없는
    -0.43
     때문에
    -0.42
     Braga
    -0.42
    дента
    -0.42
    POSITIVE LOGITS
     endforeach
    0.73
     onCancelled
    0.60
    LookAnd
    0.57
     ainfi
    0.56
     WaitForSeconds
    0.56
     ſur
    0.55
    BeginInit
    0.53
    ambién
    0.53
     isInitialized
    0.52
     sánchez
    0.52
    Act Density 0.004%

    No Known Activations