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

    Neuronpedia

    INDEX
    Explanations

    reject / module / concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    시
    0.49
    Fecha
    0.46
    體
    0.46
    いた
    0.45
    Thro
    0.45
    就
    0.45
    τα
    0.45
    ताल
    0.44
    물
    0.43
    보
    0.43
    POSITIVE LOGITS
    lak
    0.47
     anthropology
    0.46
     elektrom
    0.46
     astrophys
    0.45
     anthropologists
    0.44
     Ok
    0.44
     köy
    0.43
    nap
    0.43
     pst
    0.43
     जादू
    0.43
    Act Density 0.001%

    No Known Activations