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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     모든
    -0.07
    .Green
    -0.07
    -established
    -0.07
     Details
    -0.07
    ipated
    -0.07
     stuffed
    -0.07
    uracion
    -0.07
     skilled
    -0.06
    干扰
    -0.06
     Confirm
    -0.06
    POSITIVE LOGITS
     precedent
    0.08
     privat
    0.07
    	Editor
    0.07
    实践
    0.07
     JsonConvert
    0.07
     commod
    0.06
    gence
    0.06
     entrev
    0.06
    Identity
    0.06
    _UNDER
    0.06
    Act Density 0.022%

    No Known Activations