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

    Neuronpedia

    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ermann
    -0.07
    -writing
    -0.07
    pty
    -0.07
    其实
    -0.07
     os
    -0.07
    uy
    -0.06
    TRACT
    -0.06
    aming
    -0.06
    obil
    -0.06
     unfit
    -0.06
    POSITIVE LOGITS
     Иванов
    0.07
     Bah
    0.07
    _Parms
    0.07
     Shader
    0.06
     UNIT
    0.06
     Vladim
    0.06
     Πέ
    0.06
    (completion
    0.06
     upd
    0.06
    .IN
    0.06
    Act Density 0.135%

    No Known Activations