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

    Neuronpedia

    INDEX
    Explanations

    code-related keywords and terms associated with programming or software development

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

    cost or value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Moff
    -0.47
    ErrUnexpectedEOF
    -0.46
    ずつ
    -0.46
    verdad
    -0.45
    GEBURTSDATUM
    -0.44
     magasiner
    -0.43
    msgTypes
    -0.42
     VIAF
    -0.42
     DeV
    -0.42
    nuevo
    -0.39
    POSITIVE LOGITS
     сто
    1.34
     стоит
    1.00
    Сто
    0.97
     Сто
    0.82
     стоят
    0.71
     stojí
    0.59
    กร
    0.57
     tròn
    0.56
    stdc
    0.53
    ########.
    0.53
    Act Density 0.003%

    No Known Activations