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

    Neuronpedia

    INDEX
    Explanations

    braces and semicolons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Output
    -0.07
     Analyzer
    -0.07
     cấp
    -0.07
     zvý
    -0.07
    _DISTANCE
    -0.06
     africa
    -0.06
    dds
    -0.06
     Time
    -0.06
    Serve
    -0.06
     Flat
    -0.06
    POSITIVE LOGITS
    Reject
    0.06
    aghetti
    0.06
    ujemy
    0.06
    >window
    0.06
     희
    0.06
     initialState
    0.06
    	wg
    0.06
     찾
    0.05
    /')
    0.05
    λή
    0.05
    Act Density 0.019%

    No Known Activations