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

    Neuronpedia

    INDEX
    Explanations

    partner's perspective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    镙
    0.24
    ເຄ
    0.22
     মোটর
    0.22
     soaking
    0.21
     agu
    0.21
     welcome
    0.21
     kinderg
    0.21
     fellow
    0.21
    みを
    0.21
     greenhouse
    0.20
    POSITIVE LOGITS
     डाटा
    0.22
    *{\
    0.20
    encoding
    0.20
    vati
    0.20
    embedding
    0.20
     души
    0.19
    匕
    0.19
    Raises
    0.19
     количество
    0.19
    price
    0.19
    Act Density 0.002%

    No Known Activations