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

    Neuronpedia

    INDEX
    Explanations

    various forms of challenges and their implications within different contexts

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

    defining place or situation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OMITBAD
    -0.54
     DBNull
    -0.50
    uxxxx
    -0.45
     gelap
    -0.44
    Autoritní
    -0.43
     autorytatywna
    -0.43
    Пря
    -0.42
    ngdoc
    -0.42
    rungsseite
    -0.41
    zeitige
    -0.41
    POSITIVE LOGITS
     canst
    0.43
    mentet
    0.38
     ſon
    0.36
     themſelves
    0.36
    ‍♀️
    0.35
    ‍♂️
    0.35
     montagnes
    0.34
     greateſt
    0.34
     disponibilités
    0.34
     shalt
    0.34
    Act Density 0.389%

    No Known Activations