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

    Neuronpedia

    INDEX
    Explanations

    reference markers or indicators in the text

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

    after specific tokens (, Q, Field)

    np_acts-logits-general · gemini-2.0-flash

    no regrets or worst outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegistryLite
    -0.86
    addPreferredGap
    -0.76
    CppMethod
    -0.71
    ++]=
    -0.67
    OGND
    -0.66
     Efq
    -0.64
     gradova
    -0.63
    AutoField
    -0.62
    CreateModel
    -0.62
    ]='\
    -0.62
    POSITIVE LOGITS
     nor
    1.33
     anymore
    0.98
     tampoco
    0.93
     either
    0.80
    nor
    0.78
     nici
    0.78
     sondern
    0.76
     any
    0.76
    Nor
    0.75
     nicio
    0.73
    Act Density 0.336%

    No Known Activations