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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dh
    -0.06
     ns
    -0.06
     kettle
    -0.06
    .fr
    -0.06
     relaxing
    -0.06
     upsetting
    -0.06
    roup
    -0.06
    	exp
    -0.06
    }).
    -0.06
     feat
    -0.06
    POSITIVE LOGITS
     "','
    0.07
     Metric
    0.06
     Lair
    0.06
    рование
    0.06
    ERİ
    0.06
    $val
    0.06
     ><?
    0.06
     nhánh
    0.06
     recruitment
    0.06
     getContent
    0.06
    Act Density 0.046%

    No Known Activations