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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Prob
    -0.07
     list
    -0.07
    Bel
    -0.06
    Objective
    -0.06
     previews
    -0.06
    亚
    -0.06
     PDF
    -0.06
     lists
    -0.06
     oblast
    -0.06
    amment
    -0.06
    POSITIVE LOGITS
     thập
    0.06
    	ds
    0.06
     }//
    0.06
    cies
    0.06
     posled
    0.06
    _True
    0.06
    _take
    0.06
    ascending
    0.06
    _Result
    0.06
    .ng
    0.06
    Act Density 0.366%

    No Known Activations