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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters with varying frequencies in a statistical context

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

    Probability of picking certain letters

    np_acts-logits-general · gemini-2.0-flash

    probability of letter combinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.73
    ſelf
    -0.70
     nakalista
    -0.70
     Normdatei
    -0.68
    parsedMessage
    -0.68
    /*
    -0.67
    دانشنامهٔ
    -0.67
    GEBURTSDATUM
    -0.65
    findpost
    -0.64
    adpleegd
    -0.63
    POSITIVE LOGITS
     letter
    0.79
     vowel
    0.73
     letters
    0.71
     consonants
    0.69
     vowels
    0.67
     huruf
    0.66
    letter
    0.64
    Letter
    0.63
     Letter
    0.62
    vowel
    0.61
    Act Density 0.243%

    No Known Activations