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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or values

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

    text after system prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    서
    -0.36
     pitch
    -0.33
    ArrowToggle
    -0.32
    作
    -0.32
    F
    -0.32
     scomp
    -0.31
     tête
    -0.31
     приходи
    -0.30
    ziej
    -0.30
     top
    -0.30
    POSITIVE LOGITS
     BoxFit
    0.71
     poffible
    0.64
     queſta
    0.63
    FormTagHelper
    0.62
     AssemblyProduct
    0.60
    最快更新
    0.60
    endphp
    0.59
     myſelf
    0.59
     miniaturka
    0.57
    ientras
    0.56
    Act Density 0.000%

    No Known Activations