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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies and their findings

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

    post-mortem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jooq
    -0.49
    /**
    -0.47
     '\\;'
    -0.45
    yntaxException
    -0.44
    -£
    -0.42
    spaceBetween
    -0.40
     StringTokenizer
    -0.40
    AllAfrica
    -0.39
    rawDesc
    -0.39
    \{\\
    -0.39
    POSITIVE LOGITS
    帖最后由
    0.46
     Италијани
    0.43
    OGND
    0.42
     Acceler
    0.42
     يتيمه
    0.41
    xodo
    0.41
    RTCK
    0.40
     osa
    0.40
    Décès
    0.40
    хьтан
    0.39
    Act Density 0.358%

    No Known Activations