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

    Neuronpedia

    INDEX
    Explanations

    Adding extra space/margin

    np_max-act · gemini-2.0-flash

    This neuron detects technical engineering terms denoting design parameters or considerations—especially words referring to loads, forces, safety factors, and similar seismic‐design criteria.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     checkboxes
    -0.07
    만원
    -0.06
     textStyle
    -0.06
     Qualified
    -0.06
    GetInstance
    -0.06
    (newValue
    -0.06
     daher
    -0.06
    Digit
    -0.06
     charg
    -0.06
     hashtable
    -0.06
    POSITIVE LOGITS
    Classic
    0.07
     carne
    0.06
    ardy
    0.06
    urvey
    0.06
    ALAR
    0.06
    >Main
    0.06
    abal
    0.06
     electorate
    0.06
    iju
    0.06
     mortar
    0.06
    Act Density 0.062%

    No Known Activations