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

    Neuronpedia

    INDEX
    Explanations

    cooling, focus, belts, heat, face, furnaces, muscle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.68
     using
    0.65
     use
    0.59
     include
    0.56
     edible
    0.54
     insurgency
    0.54
     see
    0.53
    ัพท์
    0.52
     R
    0.52
     C
    0.51
    POSITIVE LOGITS
    u
    0.66
    i
    0.62
    at
    0.61
    ي
    0.58
    in
    0.57
    ม
    0.55
    Time
    0.54
    on
    0.54
    as
    0.53
    و
    0.53
    Act Density 0.116%

    No Known Activations