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

    Neuronpedia

    INDEX
    Explanations

    size

    np_max-act · gemini-2.0-flash

    The neuron detects decimal (floating‐point) numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ónico
    -0.06
    methods
    -0.06
     tốt
    -0.06
     eof
    -0.06
    .";
    -0.05
    ूछ
    -0.05
     слова
    -0.05
     criter
    -0.05
    Το
    -0.05
     Thief
    -0.05
    POSITIVE LOGITS
     ".$_
    0.07
     investigative
    0.07
     który
    0.06
     bardzo
    0.06
    GM
    0.06
    >".$
    0.06
    บบ
    0.06
    (prompt
    0.06
     autonom
    0.06
    뢰
    0.06
    Act Density 0.390%

    No Known Activations