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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming interfaces and error handling

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

    Code or special characters

    np_acts-logits-general · gemini-2.0-flash

    code and technical text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegistryLite
    -0.68
     للمعارف
    -0.56
     المعيارى
    -0.55
    anet
    -0.53
    antMatchers
    -0.52
    ())).
    -0.52
    ತ್
    -0.52
    ())->
    -0.51
    ))->
    -0.50
    addPreferredGap
    -0.50
    POSITIVE LOGITS
    的话
    0.73
    的話
    0.67
     interesa
    0.66
    IsContent
    0.59
    UnsafeEnabled
    0.56
    tilhe
    0.55
     hadn
    0.55
     aught
    0.54
     concernés
    0.54
     quelcon
    0.53
    Act Density 0.112%

    No Known Activations