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

    Neuronpedia

    INDEX
    Explanations

    terms related to maximum and minimum values

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

    MAX constants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prêtres
    -0.48
    httphttps
    -0.47
     berarti
    -0.45
     scolaires
    -0.44
    ckså
    -0.42
     navires
    -0.42
    trucks
    -0.42
     BoxDecoration
    -0.42
     videojuegos
    -0.41
     âmes
    -0.41
    POSITIVE LOGITS
    MAX
    1.65
     MAX
    1.28
     MIN
    0.60
    MIN
    0.60
    UserScript
    0.51
    INVALID
    0.45
    Hentet
    0.45
     Maxim
    0.44
    complexContent
    0.44
    MaxValue
    0.44
    Act Density 0.010%

    No Known Activations