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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to statistical data or metrics

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

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ッソ
    -0.36
     Poc
    -0.33
     depth
    -0.33
     Bloomington
    -0.32
     scarlet
    -0.32
     Kate
    -0.32
     details
    -0.32
     Super
    -0.32
     department
    -0.32
    Вели
    -0.31
    POSITIVE LOGITS
     beginnetje
    0.82
    SharedCtor
    0.81
    ValueStyle
    0.72
    rungsseite
    0.68
     autorytatywna
    0.68
     Numerade
    0.68
    tagHelperRunner
    0.66
     disambiguazione
    0.65
    AndEndTag
    0.65
    CloseOperation
    0.63
    Act Density 0.048%

    No Known Activations