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

    Neuronpedia

    INDEX
    Explanations

    components and configurations related to software development, particularly with regard to templates and references

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

    config keywords and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amento
    -0.42
    ITAT
    -0.36
    stration
    -0.35
    دانشنامهٔ
    -0.34
     faibles
    -0.33
    ppe
    -0.33
    юз
    -0.32
    atchewan
    -0.32
     ered
    -0.32
     tpu
    -0.32
    POSITIVE LOGITS
    BeginContext
    0.63
    Personendaten
    0.63
    exitRule
    0.61
    fromnode
    0.59
     ujednoznacz
    0.59
     للاسماء
    0.57
    principalColumn
    0.56
    bkz
    0.56
    oa̍t
    0.56
     مشين
    0.55
    Act Density 0.237%

    No Known Activations