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

    Neuronpedia

    INDEX
    Explanations

    cellspacing

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on floating‐point numeric literals (i.e. numbers with decimal points).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Ber
    -0.07
    OrFail
    -0.07
    ie
    -0.06
    .snapshot
    -0.06
    rido
    -0.06
     元
    -0.06
    ed
    -0.06
     única
    -0.06
    (QL
    -0.06
    antaged
    -0.06
    POSITIVE LOGITS
     cellspacing
    0.12
    )↵↵↵
    0.07
    393
    0.07
     Malay
    0.07
     Apartments
    0.06
    stroke
    0.06
    aysia
    0.06
    ARNING
    0.06
     रखत
    0.06
     newList
    0.06
    Act Density 0.000%

    No Known Activations