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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Кроме
    -0.07
     Bren
    -0.07
     pending
    -0.07
    vero
    -0.07
     strr
    -0.07
    <P
    -0.07
    _PICK
    -0.07
     OS
    -0.06
     inev
    -0.06
    839
    -0.06
    POSITIVE LOGITS
     he
    0.11
     they
    0.10
     we
    0.09
     They
    0.08
     she
    0.08
    They
    0.08
     you
    0.07
    .
    0.07
     it
    0.07
     It
    0.06
    Act Density 0.711%

    No Known Activations