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

    Neuronpedia

    INDEX
    Explanations

    unique tokens or identifiers in code-like structures

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

    Text containing numbers and punctuation

    np_acts-logits-general · gemini-2.0-flash

    dates and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -0.83
     Monfieur
    -0.82
     Majefty
    -0.75
     Jefus
    -0.74
     poffe
    -0.74
     leaſt
    -0.74
     Diſ
    -0.73
     Inscrivez
    -0.72
     myſelf
    -0.72
     becauſe
    -0.72
    POSITIVE LOGITS
     OFDb
    0.71
    PreInfinity
    0.63
     poveznice
    0.61
    Parcelize
    0.57
    AnimationsModule
    0.52
    XmlAccessType
    0.50
     carriera
    0.47
    ỡng
    0.47
    cześ
    0.47
     externi
    0.46
    Act Density 0.159%

    No Known Activations