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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating successful outcomes or functionality

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

    Describes something working well

    np_acts-logits-general · gemini-2.0-flash

    functioning properly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.81
    rungsseite
    -0.77
     AssemblyProduct
    -0.71
    InvalidProtocol
    -0.71
     nahilalakip
    -0.69
    sibirsk
    -0.68
    URLException
    -0.66
    ScopeManager
    -0.61
    ⓧ
    -0.60
     متعلقه
    -0.60
    POSITIVE LOGITS
     flawlessly
    0.78
     smoothly
    0.76
     wonders
    0.76
     properly
    0.73
     reliably
    0.73
     great
    0.71
     einwand
    0.70
     fine
    0.66
     seamlessly
    0.65
     correctly
    0.61
    Act Density 0.109%

    No Known Activations