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

    Neuronpedia

    INDEX
    Explanations

    references to dates and numerical values related to events or statistics

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

    years in text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dAtA
    -0.45
    évaluateur
    -0.43
     NAC
    -0.41
    edance
    -0.38
    ställning
    -0.38
    vábbi
    -0.36
    NAC
    -0.36
     BCM
    -0.36
     tamp
    -0.35
    AnimationsModule
    -0.35
    POSITIVE LOGITS
     ibunya
    0.57
     للمعارف
    0.57
    zbęd
    0.56
     mães
    0.53
    ValueStyle
    0.52
    delwed
    0.50
     miliardi
    0.50
     biografias
    0.49
     independently
    0.49
     when
    0.47
    Act Density 0.137%

    No Known Activations