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

    Neuronpedia

    INDEX
    Explanations

    expression in eyes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     everyday
    0.40
     deceased
    0.38
     BD
    0.37
     justifications
    0.36
     daytime
    0.36
     barrel
    0.35
     facial
    0.35
     নন
    0.35
    руют
    0.35
     yellowish
    0.35
    POSITIVE LOGITS
    Horse
    0.44
    Energy
    0.43
     书
    0.43
    。\
    0.43
    水
    0.43
     물
    0.42
     وسی
    0.42
    Borrow
    0.41
    (/[
    0.40
    CipherText
    0.40
    Act Density 0.004%

    No Known Activations