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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    建築
    -0.07
    skb
    -0.06
    |RF
    -0.06
    Rock
    -0.06
    ्ब
    -0.06
    이라
    -0.06
     they
    -0.06
    哭
    -0.06
    تب
    -0.06
     we
    -0.06
    POSITIVE LOGITS
     Of
    0.07
     Enough
    0.06
     At
    0.06
     Shotgun
    0.06
     Sent
    0.06
     By
    0.06
    δικ
    0.06
    "><?=$
    0.06
    _Per
    0.06
    .At
    0.06
    Act Density 1.598%

    No Known Activations