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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations

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

    math expressions with symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kaynağından
    -0.43
     muerta
    -0.42
     antigüedad
    -0.39
     muerto
    -0.37
     nueces
    -0.36
    enumii
    -0.36
    extrême
    -0.36
     herido
    -0.36
     inscrição
    -0.33
    âmara
    -0.33
    POSITIVE LOGITS
     betweenstory
    0.69
     surla
    0.68
     queſta
    0.60
     ſind
    0.57
    localctx
    0.55
    最快更新
    0.55
    BibitemShut
    0.54
     zwiſchen
    0.54
     fashiola
    0.53
    ValueStyle
    0.52
    Act Density 0.105%

    No Known Activations