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

    Neuronpedia

    INDEX
    Explanations

    terms related to numerical data or quantities

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

    <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    迹
    -0.36
     locally
    -0.35
     Bras
    -0.35
     Buch
    -0.35
    ModelMap
    -0.34
     N
    -0.34
    ELDS
    -0.34
    淀
    -0.34
     Carvalho
    -0.34
     Mitchell
    -0.33
    POSITIVE LOGITS
     Chwiliwch
    0.69
    fitrión
    0.68
    NameInMap
    0.68
     мәкал
    0.66
    parsedMessage
    0.66
     Biôgrafia
    0.63
     Numerade
    0.63
     ब्रेकडाउन
    0.62
     Italijanski
    0.61
     kasarigan
    0.60
    Act Density 0.000%

    No Known Activations