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

    Neuronpedia

    INDEX
    Explanations

    199

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    стре
    -0.07
     knob
    -0.06
    �
    -0.06
     shareholders
    -0.06
    <Course
    -0.06
    ▍
    -0.06
    hq
    -0.06
     yapılır
    -0.06
     پاورپوینت
    -0.05
     Rodr
    -0.05
    POSITIVE LOGITS
     تلك
    0.07
     scrap
    0.07
     سیاست
    0.07
     Tesla
    0.07
     temas
    0.07
     vista
    0.06
     volcanic
    0.06
     uncertainty
    0.06
     Portsmouth
    0.06
     ENC
    0.06
    Act Density 0.006%

    No Known Activations