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

    Neuronpedia

    INDEX
    Explanations

    names of substances, their effects, or specific functions in scientific contexts

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

    chemical or mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mar
    -0.40
    ↵
    -0.35
     Sco
    -0.34
     Sch
    -0.32
     Cer
    -0.32
     H
    -0.32
     Gal
    -0.32
     Ris
    -0.31
     Del
    -0.30
     Lav
    -0.30
    POSITIVE LOGITS
     ModelExpression
    0.93
     AssemblyCompany
    0.78
     itſelf
    0.77
     myſelf
    0.77
     Theſe
    0.76
     Geſ
    0.75
     queſta
    0.75
     desmotivaciones
    0.74
     pleaſure
    0.74
     increí
    0.71
    Act Density 0.175%

    No Known Activations