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

    Neuronpedia

    INDEX
    Explanations

    on-device tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     therein
    0.49
     இதில்
    0.45
     preferentially
    0.42
     Hopefully
    0.41
     thereon
    0.41
    unia
    0.41
     Preferably
    0.40
     preferably
    0.40
     इसमें
    0.39
     उसमें
    0.38
    POSITIVE LOGITS
    为了
    0.48
    '=>'
    0.46
     为了
    0.44
    為了
    0.43
    Mission
    0.42
    اونلو
    0.42
    Descripción
    0.42
    Task
    0.41
    ibbean
    0.41
    tasks
    0.40
    Act Density 0.001%

    No Known Activations