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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unfamiliarity or lack of awareness about certain topics or subjects

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

    Following "never," "ever," or "heard"

    np_acts-logits-general · gemini-2.0-flash

    ever heard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ranslated
    -0.53
     complémentaires
    -0.47
    дован
    -0.46
    anches
    -0.46
    rews
    -0.45
    chiede
    -0.45
    ToLeft
    -0.45
     brevis
    -0.45
     valoraciones
    -0.44
     nokt
    -0.43
    POSITIVE LOGITS
    +#+#
    0.77
     المعيارى
    0.68
    matchCondition
    0.66
     exper
    0.63
    SPATH
    0.62
     onCreateView
    0.62
     ever
    0.60
     wireType
    0.59
     للمعارف
    0.59
     ExecuteAsync
    0.58
    Act Density 0.116%

    No Known Activations