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

    Neuronpedia

    INDEX
    Explanations

    `image` coordinate `level`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    segaretro
    0.39
     جنيه
    0.39
     پوچھ
    0.38
    ạng
    0.38
     р
    0.37
    味噌
    0.37
    铢
    0.37
    ответ
    0.37
     bungalow
    0.36
    ثل
    0.36
    POSITIVE LOGITS
     Sensor
    0.46
     Modal
    0.43
     Den
    0.41
     modal
    0.40
    Den
    0.38
     Dialog
    0.38
    वास
    0.38
     Empty
    0.38
     Awesome
    0.38
     Digital
    0.38
    Act Density 0.000%

    No Known Activations