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

    Neuronpedia

    INDEX
    Explanations

    top side edge regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilitas
    0.85
    要求的
    0.74
    fromString
    0.73
    抬头
    0.72
     useParams
    0.72
     anlaş
    0.71
    መ
    0.71
     தன்ன
    0.70
    በ
    0.70
     አይነት
    0.70
    POSITIVE LOGITS
     side
    1.63
    most
    1.48
     edge
    1.42
     portion
    1.34
    쪽
    1.29
    側の
    1.25
    ward
    1.24
    สุด
    1.23
    側に
    1.23
    side
    1.18
    Act Density 0.205%

    No Known Activations