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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical data and related expressions

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

    Numbers and mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -1.11
    Autoritní
    -0.79
    +#+#
    -0.71
     يتيمه
    -0.70
    FieldOffset
    -0.66
    RunWith
    -0.66
    Filmografie
    -0.65
    \{\\
    -0.63
     SIAM
    -0.63
    SOUNDBITE
    -0.63
    POSITIVE LOGITS
    脚注の使い方
    0.73
    addGap
    0.55
     sekal
    0.48
    agaimana
    0.42
     oprot
    0.40
     $^{
    0.40
     Коро
    0.40
    fitriones
    0.39
    Wię
    0.39
    oneofs
    0.39
    Act Density 0.392%

    No Known Activations