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

    Neuronpedia

    INDEX
    Explanations

    *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     परंतु
    0.47
    ganggu
    0.45
    trone
    0.45
     valle
    0.44
    vorschau
    0.43
     barons
    0.42
     provincial
    0.42
    ově
    0.42
     ważne
    0.42
    vr
    0.41
    POSITIVE LOGITS
    𝐾
    0.45
     reagents
    0.45
     각
    0.44
    血液
    0.43
     ？
    0.42
    Ｉ
    0.42
    Measurement
    0.40
     Replies
    0.40
     Emissions
    0.40
     currencies
    0.39
    Act Density 0.003%

    No Known Activations