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

    Neuronpedia

    INDEX
    Explanations

    freedom

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens representing floating-point values (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     пацієн
    -0.08
    yards
    -0.07
    PACE
    -0.07
    Return
    -0.06
    IDENT
    -0.06
     whole
    -0.06
    ст
    -0.06
     GLES
    -0.06
     Trade
    -0.06
    _QUAL
    -0.06
    POSITIVE LOGITS
    utes
    0.07
    xCD
    0.07
     vyh
    0.06
     PCS
    0.06
    .'/
    0.06
     wy
    0.06
    _months
    0.06
     ',
    0.06
     ade
    0.06
     TODAY
    0.06
    Act Density 0.006%

    No Known Activations