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

    Neuronpedia

    INDEX
    Explanations

    path, PathType, size, device, off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    镜头
    0.40
    geqq
    0.39
     diathermy
    0.38
    Lengths
    0.38
    ிறார்
    0.36
     नाथ
    0.36
    ल्लभ
    0.36
    ᖏ
    0.36
     स्कैनर
    0.36
    ÔNG
    0.36
    POSITIVE LOGITS
    all
    0.38
    pro
    0.36
     session
    0.36
     graduate
    0.35
     p
    0.35
     access
    0.35
     wra
    0.35
    (
    0.35
    —
    0.35
    alta
    0.34
    Act Density 0.003%

    No Known Activations