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

    Neuronpedia

    INDEX
    Explanations

    supreme

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     continuous
    -0.07
    �
    -0.07
     eget
    -0.07
     ez
    -0.07
     ak
    -0.06
    )/(
    -0.06
     וה
    -0.06
    izzes
    -0.06
    aven
    -0.06
    ,cljs
    -0.06
    POSITIVE LOGITS
    ündig
    0.07
     twó
    0.07
    :frame
    0.07
    �
    0.07
    rä
    0.07
    �체
    0.06
    纰
    0.06
    rotch
    0.06
    $data
    0.06
    Deal
    0.06
    Act Density 0.002%

    No Known Activations