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

    Neuronpedia

    INDEX
    Explanations

    lists of items or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    枌
    0.26
     مذہ
    0.23
     parturient
    0.23
    죤
    0.23
    SCHRAMM
    0.23
     simonsen
    0.22
    ULS
    0.22
    öffentlichung
    0.22
     humains
    0.22
     obstru
    0.22
    POSITIVE LOGITS
    T
    0.28
    i
    0.27
    k
    0.26
    a
    0.26
    re
    0.25
    ay
    0.25
    s
    0.25
    v
    0.25
    ro
    0.24
    the
    0.24
    Act Density 0.001%

    No Known Activations