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

    Neuronpedia

    INDEX
    Explanations

    examination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    られた
    -0.06
    وج
    -0.06
    岡
    -0.06
     ног
    -0.06
    gart
    -0.06
     đảng
    -0.06
     Christoph
    -0.06
     Studi
    -0.06
    dd
    -0.06
    .Settings
    -0.05
    POSITIVE LOGITS
    �
    0.07
    ина
    0.07
    PRO
    0.07
    cedes
    0.07
     CONSEQUENTIAL
    0.07
     struggle
    0.07
     backdrop
    0.07
    antages
    0.06
     delimited
    0.06
    stitution
    0.06
    Act Density 0.024%

    No Known Activations