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

    Neuronpedia

    INDEX
    Explanations

    terms related to positive attributes or outcomes in various contexts

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

    positive roots, integers, or regulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    áctenos
    -0.57
    InitVars
    -0.55
     getRule
    -0.48
    erçe
    -0.48
     SwitchCompat
    -0.47
     Unterricht
    -0.47
     verheiratet
    -0.47
    chond
    -0.46
    yszer
    -0.46
    iconque
    -0.46
    POSITIVE LOGITS
     positive
    2.13
     Positive
    2.11
    Positive
    2.09
    positive
    1.99
     POSITIVE
    1.81
    POSITIVE
    1.80
     positiva
    1.51
     positivo
    1.49
     positively
    1.45
     positives
    1.41
    Act Density 0.024%

    No Known Activations