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
     μό
    -0.07
     getById
    -0.07
    будь
    -0.06
     BE
    -0.06
    вид
    -0.06
     H�
    -0.06
     })).
    -0.06
    šní
    -0.06
    スタ
    -0.06
    /Branch
    -0.06
    POSITIVE LOGITS
    aname
    0.07
    .emit
    0.07
    toUpperCase
    0.07
    ceries
    0.06
     nums
    0.06
    ف
    0.06
     JSONObject
    0.06
    (endpoint
    0.06
     convertView
    0.06
    (entity
    0.06
    Act Density 0.014%

    No Known Activations