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

    Neuronpedia

    INDEX
    Explanations

    instances of the apostrophe used for contractions or possessives

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

    dialogue or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -1.04
    verwijspagina
    -0.76
     يتيمه
    -0.75
    ſelves
    -0.72
     arşivlendi
    -0.71
     defaultstate
    -0.71
    +#+#
    -0.70
     виправивши
    -0.66
     MainAxisSize
    -0.65
     HasFactory
    -0.64
    POSITIVE LOGITS
    !
    0.61
    s
    0.54
    _
    0.50
     Nixon
    0.49
    ing
    0.47
    !)
    0.46
    ,
    0.46
     Pi
    0.44
     Jim
    0.42
     Welsh
    0.41
    Act Density 0.008%

    No Known Activations