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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations involving variables and functions

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

    mathematical and code expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GroupLayout
    -0.40
    渡
    -0.36
     inte
    -0.34
    ٍ
    -0.32
     denn
    -0.31
    RetentionPolicy
    -0.31
     Apo
    -0.30
     strategy
    -0.30
     soll
    -0.29
     event
    -0.28
    POSITIVE LOGITS
     Geſch
    0.74
    脚注の使い方
    0.67
     Geſ
    0.64
    تقاوى
    0.61
    endpush
    0.61
    stdc
    0.60
     AssemblyTitle
    0.60
    曖昧さ回避
    0.59
     eletrônico
    0.59
     ainfi
    0.59
    Act Density 0.173%

    No Known Activations