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

    Neuronpedia

    INDEX
    Explanations

    Feature

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .....↵↵
    -0.08
    decision
    -0.07
    .testing
    -0.07
    owering
    -0.07
    packages
    -0.07
    (dead
    -0.07
     cushion
    -0.07
    准
    -0.07
    确立
    -0.07
    constitutional
    -0.07
    POSITIVE LOGITS
    ologie
    0.07
     Spy
    0.06
    geries
    0.06
     instructors
    0.06
    .addValue
    0.06
    Rew
    0.06
     Boys
    0.06
     更
    0.06
     Twe
    0.06
     Gn
    0.06
    Act Density 0.001%

    No Known Activations