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

    Neuronpedia

    INDEX
    Explanations

    references to software updates and technical documentation

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

    Strings that include special characters

    np_acts-logits-general · gemini-2.0-flash

    math symbols and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁿
    -1.31
    μβρίου
    -0.84
    }{*}{}
    -0.81
    endphp
    -0.77
     سكانية
    -0.77
    __*/
    -0.75
    WithFormat
    -0.72
    intios
    -0.68
    Personensuche
    -0.67
    UVWXYZ
    -0.64
    POSITIVE LOGITS
     تعدى
    0.63
     fhew
    0.61
    .*")]
    0.60
    المراجع
    0.60
     AssemblyCompany
    0.59
     caufe
    0.58
    页面存档备份
    0.57
    ﹍﹍﹍
    0.57
     Majefty
    0.56
    Fordítás
    0.56
    Act Density 6.501%

    No Known Activations