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

    Neuronpedia

    INDEX
    Explanations

    elements related to operational parameters and conditions in programming or data processing contexts

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

    Word preceding a quantitative value

    np_acts-logits-general · gemini-2.0-flash

    comparisons and extremes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.75
    httphttps
    -0.74
     يتيمه
    -0.69
    ︐
    -0.68
    parsedMessage
    -0.68
     AssemblyTitle
    -0.67
    хьтан
    -0.67
     kasarigan
    -0.67
     fashiola
    -0.66
    🜲
    -0.66
    POSITIVE LOGITS
     sebaliknya
    0.42
    ↵↵
    0.37
    ){}
    0.34
     circunstancias
    0.33
    seiti
    0.31
    Another
    0.31
     plutôt
    0.30
    ↵↵↵
    0.29
     تكبرها
    0.29
    <eos>
    0.28
    Act Density 3.268%

    No Known Activations