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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing surprise or emphasis on reasoning

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

    indeed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AISSEE
    -0.58
    NameInMap
    -0.54
     Verſ
    -0.49
    majánló
    -0.48
    不信
    -0.48
     distinto
    -0.48
    üğü
    -0.47
    lső
    -0.47
    XmlAccessorType
    -0.47
     promesa
    -0.47
    POSITIVE LOGITS
    EndInit
    0.45
    wpdb
    0.44
     rewarded
    0.43
    ResumeLayout
    0.40
    didSet
    0.39
    propTypes
    0.38
     HasFactory
    0.38
     '\\;'
    0.38
     indeed
    0.37
     denn
    0.36
    Act Density 0.024%

    No Known Activations