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

    Neuronpedia

    INDEX
    Explanations

    cloud providers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    できます
    0.42
    分かる
    0.41
     دهد
    0.40
    ສາມາດ
    0.40
    您可以
    0.39
    स्टूड
    0.37
     możemy
    0.36
    lwjglVersion
    0.35
     (\<
    0.35
     ይችላሉ
    0.35
    POSITIVE LOGITS
     Optim
    0.49
    lack
    0.48
     Latin
    0.46
    latin
    0.43
     हारा
    0.43
     latin
    0.42
     latino
    0.41
    azio
    0.41
    0.41
    lost
    0.41
    Act Density 0.000%

    No Known Activations