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

    Neuronpedia

    INDEX
    Explanations

    references to specific items or products

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

    early use different

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.45
     <=",
    -0.43
    flich
    -0.42
     незавершена
    -0.42
    исленность
    -0.41
     engraçadas
    -0.41
    談社
    -0.40
     jadx
    -0.40
     anaknya
    -0.40
     tecnici
    -0.39
    POSITIVE LOGITS
    AndEndTag
    0.51
     faſt
    0.43
     noDo
    0.42
    KURZBESCHREIBUNG
    0.41
    ſelf
    0.39
    AsStream
    0.38
    يميديا
    0.38
    RLock
    0.37
    waltung
    0.37
     przec
    0.36
    Act Density 0.005%

    No Known Activations