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

    Neuronpedia

    INDEX
    Explanations

    predicting possibility or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }
    0.47
     aeration
    0.46
    }
    0.45
    poor
    0.42
    ра
    0.42
     $
    0.41
    ine
    0.41
    pain
    0.41
    corre
    0.41
    Poor
    0.41
    POSITIVE LOGITS
    ሮች
    0.46
    かもしれませんが
    0.44
    dDays
    0.44
     fortale
    0.43
    那些
    0.43
    お客様
    0.41
    MaxPooling
    0.40
     유럽
    0.40
     preferring
    0.39
     یورپی
    0.39
    Act Density 0.022%

    No Known Activations