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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating requirements or conditions

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

    setting parameter values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlAccessorType
    -0.46
     foolish
    -0.42
    raborty
    -0.42
     foolishness
    -0.41
     banish
    -0.41
    〆
    -0.41
    PullParser
    -0.41
    فو
    -0.41
     shunned
    -0.41
    .*")]
    -0.40
    POSITIVE LOGITS
     AssemblyCulture
    0.63
    IContainer
    0.53
    Gweler
    0.46
     values
    0.46
     Reſ
    0.45
    UnifiedTopology
    0.44
     itinéraires
    0.43
    ambién
    0.43
     Comprometido
    0.42
     étoient
    0.41
    Act Density 0.000%

    No Known Activations