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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence structures

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

    academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.81
    berdayakan
    -0.62
    AnchorStyles
    -0.61
    )_/¯
    -0.57
     gawas
    -0.56
    iach
    -0.55
     MainAxisSize
    -0.53
     виправивши
    -0.53
     focussed
    -0.52
    прочем
    -0.51
    POSITIVE LOGITS
     Somit
    0.47
     ujedno
    0.46
    aktery
    0.46
     Richtlinien
    0.45
     Nowadays
    0.44
     respective
    0.44
     perciò
    0.44
    Égypte
    0.44
     poiché
    0.43
     nowadays
    0.43
    Act Density 0.167%

    No Known Activations