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

    Neuronpedia

    INDEX
    Explanations

    technical terms and metrics related to experimental data or conditions

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

    Numbers followed by prepositions or connectives

    np_acts-logits-general · gemini-2.0-flash

    numbers and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.86
     autorytatywna
    -0.83
    IsMutable
    -0.83
     AssemblyCulture
    -0.82
     otomatig
    -0.81
     Italijanski
    -0.77
    oa̍t
    -0.75
     незавершена
    -0.74
    Hentet
    -0.71
    Havolalar
    -0.67
    POSITIVE LOGITS
     through
    0.80
     až
    0.79
     hingga
    0.79
     thru
    0.77
     sampai
    0.76
     până
    0.71
     kuni
    0.68
    ,...,
    0.65
     μέχρι
    0.64
     עד
    0.63
    Act Density 1.289%

    No Known Activations