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

    Neuronpedia

    INDEX
    Explanations

    14

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on the numeral that names the base (the number immediately following “base”) in base-conversion questions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     тощо
    -0.07
     fug
    -0.06
    igate
    -0.06
    madığı
    -0.06
    (output
    -0.06
     будуть
    -0.06
    ΙΟ
    -0.06
    inish
    -0.06
     ett
    -0.06
    marshall
    -0.06
    POSITIVE LOGITS
    /edit
    0.06
    "",
    0.06
    uali
    0.06
     Generated
    0.06
     liquidity
    0.06
    Ownership
    0.06
    ()=>
    0.06
     Ens
    0.06
     Pond
    0.06
    "He
    0.06
    Act Density 0.002%

    No Known Activations