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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expectations and uncertainty

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

    conditional verbs and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.63
    rungsseite
    -0.62
    yntaxException
    -0.61
    PyExc
    -0.60
    CppMethod
    -0.60
    RTGC
    -0.59
     faſt
    -0.59
     poffible
    -0.58
    Билгалдахарш
    -0.57
     שוליים
    -0.56
    POSITIVE LOGITS
    moveToNext
    0.39
    rdf
    0.32
    Così
    0.30
    Kjelder
    0.30
    Here
    0.30
     mirrored
    0.29
    ButterKnife
    0.29
    Donc
    0.29
    wijl
    0.29
     Così
    0.28
    Act Density 1.488%

    No Known Activations