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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal number tokens (floating‐point numerals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ，却
    -0.07
     činnosti
    -0.07
    这里
    -0.06
     western
    -0.06
    assandra
    -0.06
    cluster
    -0.06
    473
    -0.06
     Monsters
    -0.06
     ears
    -0.06
     only
    -0.06
    POSITIVE LOGITS
     mediante
    0.07
    unma
    0.07
    ongan
    0.07
     В
    0.06
    sak
    0.06
     вигляді
    0.06
     moves
    0.06
    维
    0.06
    loating
    0.06
    ewear
    0.06
    Act Density 0.014%

    No Known Activations