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

    Neuronpedia

    INDEX
    Explanations

    acting for and representing someone else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toegang
    0.54
    严格
    0.53
     inclusiv
    0.53
    𝐰
    0.48
    籮
    0.48
     ebenfalls
    0.47
     Эд
    0.47
    アクセス
    0.46
    ख्ती
    0.46
     Przed
    0.46
    POSITIVE LOGITS
    t
    0.50
    ig
    0.48
    vis
    0.47
    gr
    0.45
    on
    0.44
    rahydro
    0.43
    z
    0.43
    to
    0.42
    tty
    0.42
    ite
    0.41
    Act Density 0.001%

    No Known Activations