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

    Neuronpedia

    INDEX
    Explanations

    references to adjustments or modifications in various contexts

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

    minor adjustments or tweaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PYX
    -0.44
    NameInMap
    -0.38
     []:
    -0.38
    orghini
    -0.38
     للاسماء
    -0.36
     MessageBoxIcon
    -0.36
     getItemId
    -0.34
    bison
    -0.34
     endregion
    -0.34
     المعيارى
    -0.34
    POSITIVE LOGITS
     tweak
    1.90
     tweaked
    1.78
     tweaks
    1.78
     tweaking
    1.77
     tinkering
    1.00
     adjustments
    0.99
     ajustes
    0.94
     ADJUST
    0.91
    adjust
    0.91
     adjusts
    0.88
    Act Density 0.006%

    No Known Activations