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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🥚
    -0.08
     Mỗi
    -0.07
    (PDO
    -0.07
    .Environment
    -0.06
    휩
    -0.06
    ustain
    -0.06
    cers
    -0.06
    ⺠
    -0.06
    cen
    -0.06
    涠
    -0.06
    POSITIVE LOGITS
    ဂ
    0.07
     Unary
    0.07
     redundant
    0.07
    vice
    0.06
    状元
    0.06
    visible
    0.06
    汚れ
    0.06
    字母
    0.06
     convo
    0.06
     Clan
    0.06
    Act Density 0.037%

    No Known Activations