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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Asset
    -0.07
    -pocket
    -0.07
     Willie
    -0.07
    鲊
    -0.07
    神情
    -0.07
    -License
    -0.07
     loosely
    -0.07
     gerade
    -0.07
    )const
    -0.07
     racially
    -0.07
    POSITIVE LOGITS
    オープン
    0.07
     revolt
    0.07
    (parameters
    0.07
    pe
    0.07
     Pe
    0.07
    Opp
    0.07
    悖
    0.06
     פ
    0.06
    '][
    0.06
     warped
    0.06
    Act Density 0.001%

    No Known Activations