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

    Neuronpedia

    INDEX
    Explanations

    elements related to user instructions and software operations

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

    Portuguese and French word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.56
    Autoritní
    -0.47
    طلحات
    -0.46
    Jeografia
    -0.46
    CPtr
    -0.45
     []:
    -0.44
    msgTypes
    -0.43
    ViewChild
    -0.43
    ResponseWriter
    -0.41
    TargetException
    -0.40
    POSITIVE LOGITS
    ed
    0.68
    es
    0.58
    ers
    0.57
    wards
    0.57
    uality
    0.55
    ing
    0.54
    theless
    0.53
    erà
    0.53
    ingly
    0.50
    em
    0.49
    Act Density 0.052%

    No Known Activations