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

    Neuronpedia

    INDEX
    Explanations

    dead

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     genome
    -0.07
    ети
    -0.07
    ятия
    -0.06
     Democrats
    -0.06
    だよ
    -0.06
    爵
    -0.06
    スカ
    -0.06
    °}
    -0.06
    ierte
    -0.06
    庭
    -0.06
    POSITIVE LOGITS
     ");↵↵
    0.07
    oler
    0.06
    닉
    0.06
     ngang
    0.06
     Killed
    0.06
    .WriteAllText
    0.06
    (WIN
    0.06
     SCT
    0.06
    ileş
    0.06
     разработ
    0.05
    Act Density 0.023%

    No Known Activations