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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters or digits that indicate scores or metrics in sports contexts

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

    scorelines containing numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.65
    oa̍t
    -0.56
    IndentedString
    -0.52
    Zing
    -0.52
    adaptiveStyles
    -0.52
     kasarigan
    -0.52
     Савезне
    -0.51
    íncia
    -0.50
     metic
    -0.50
    Indented
    -0.50
    POSITIVE LOGITS
     asupra
    0.37
     Audiodateien
    0.35
     totalling
    0.33
    middels
    0.32
    BeginContext
    0.32
    ]")]
    0.32
    Смотрите
    0.30
     ufficiali
    0.29
     freeze
    0.29
     aproximado
    0.29
    Act Density 0.007%

    No Known Activations