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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thổ
    -0.07
     çevres
    -0.07
    (surface
    -0.06
     Clay
    -0.06
    фектив
    -0.06
    iap
    -0.06
    Capital
    -0.06
    ptal
    -0.06
     clashed
    -0.06
     [{
    -0.06
    POSITIVE LOGITS
    getClient
    0.07
    .unlock
    0.07
     carbohydrates
    0.07
    Chan
    0.07
     onBindViewHolder
    0.06
    ListComponent
    0.06
    서관
    0.06
    	slot
    0.06
    subscriber
    0.06
     Donald
    0.06
    Act Density 0.000%

    No Known Activations