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

    Neuronpedia

    INDEX
    Explanations

    key phrases and terms related to storytelling and documentation

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

    words for official actions or findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.40
    Fiche
    -0.32
    隔
    -0.32
    handleRequest
    -0.29
     coach
    -0.29
     пере
    -0.27
     pod
    -0.27
     alto
    -0.26
     gelen
    -0.25
     ell
    -0.25
    POSITIVE LOGITS
     increí
    0.63
     Administrativna
    0.60
     mauva
    0.59
     himſelf
    0.57
     themſelves
    0.57
    IsContent
    0.56
     herself
    0.55
     Geſch
    0.55
     incrí
    0.54
     conmigo
    0.54
    Act Density 0.258%

    No Known Activations