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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝚓
    0.57
     facteurs
    0.57
    𝓗
    0.57
     코드
    0.55
    𝚙
    0.55
     liczb
    0.54
     Если
    0.54
    РА
    0.54
     방법
    0.53
    cPix
    0.53
    POSITIVE LOGITS
    he
    0.66
    t
    0.66
    ik
    0.64
    src
    0.63
    hel
    0.59
    has
    0.59
    ert
    0.57
    oh
    0.57
    an
    0.56
    st
    0.55
    Act Density 0.001%

    No Known Activations