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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    历史性
    -0.07
    警务
    -0.07
     beneath
    -0.07
     Stopwatch
    -0.07
    贫困村
    -0.07
     \''
    -0.07
    明智
    -0.07
     ebp
    -0.07
     QtAws
    -0.07
    ########################################################
    -0.06
    POSITIVE LOGITS
    REMOVE
    0.07
    albums
    0.07
    amentos
    0.07
    ISCO
    0.07
     acept
    0.07
    /v
    0.06
    ycastle
    0.06
    inha
    0.06
    regular
    0.06
    Ha
    0.06
    Act Density 0.042%

    No Known Activations