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

    Neuronpedia

    INDEX
    Explanations

    restriction in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     સત
    0.44
     spontaneous
    0.43
     spont
    0.42
    lesque
    0.40
     Quit
    0.39
    比例
    0.39
     themes
    0.38
     espont
    0.38
    ွယ်
    0.37
    portrait
    0.37
    POSITIVE LOGITS
    antage
    0.42
    اري
    0.41
     ri
    0.38
    доби
    0.38
    Faces
    0.37
    רי
    0.37
    pilot
    0.37
     ніж
    0.37
    訊
    0.36
    高手
    0.36
    Act Density 0.000%

    No Known Activations