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

    Neuronpedia

    INDEX
    Explanations

    problem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     map
    -0.08
    準
    -0.07
     MMC
    -0.06
     maps
    -0.06
     disgrace
    -0.06
    (gp
    -0.06
     bans
    -0.06
     evangelical
    -0.06
     Suite
    -0.06
     bishops
    -0.06
    POSITIVE LOGITS
     setInput
    0.07
    iola
    0.07
    šak
    0.06
     sout
    0.06
     Waterloo
    0.06
    (coords
    0.06
    .engine
    0.06
    Slim
    0.06
     compuls
    0.06
    ・━
    0.06
    Act Density 0.037%

    No Known Activations