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

    Neuronpedia

    INDEX
    Explanations

    references to degrees, levels, or amounts associated with various measures or statistics

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

    Comes after "number of" or "degree of"

    np_acts-logits-general · gemini-2.0-flash

    number of or degree of phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.71
     dizaines
    -0.65
    sptr
    -0.54
     svært
    -0.54
    __(/*!
    -0.54
     larga
    -0.53
     plenty
    -0.53
     bastante
    -0.53
     galore
    -0.52
     ganske
    -0.52
    POSITIVE LOGITS
     each
    0.78
     available
    0.77
    djangoproject
    0.73
     jaką
    0.67
    Obrázky
    0.66
    available
    0.65
     (%)
    0.64
     required
    0.64
     allowable
    0.62
     Available
    0.61
    Act Density 0.600%

    No Known Activations