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

    Neuronpedia

    INDEX
    Explanations

    whether

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ρού
    -0.06
    帖
    -0.06
    زه
    -0.06
     للأ
    -0.06
     COPYING
    -0.06
     Compile
    -0.06
    ських
    -0.06
    cp
    -0.06
     розташ
    -0.06
    ases
    -0.06
    POSITIVE LOGITS
    (rng
    0.07
     tint
    0.07
     일반
    0.07
     Volunteer
    0.06
    -touch
    0.06
     transported
    0.06
    awn
    0.06
    Mitch
    0.06
     conv
    0.06
    ################
    0.06
    Act Density 0.015%

    No Known Activations