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

    Neuronpedia

    INDEX
    Explanations

    aspects of character development and performance measurements

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

    states or changes in quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.63
    pageY
    -0.52
     ihres
    -0.52
     seines
    -0.50
     которое
    -0.49
    atal
    -0.47
    ceno
    -0.45
    Referências
    -0.45
     himself
    -0.45
     UIP
    -0.45
    POSITIVE LOGITS
    ConstraintMaker
    0.75
    Delimited
    0.67
    AddTagHelper
    0.66
     мәкалә
    0.63
     kasarigan
    0.60
    Portail
    0.60
    GenerationType
    0.59
    Erreferentziak
    0.57
    IntoConstraints
    0.57
    Aiheesta
    0.57
    Act Density 0.349%

    No Known Activations