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

    Neuronpedia

    INDEX
    Explanations

    output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Üniversit
    -0.07
    .Minimum
    -0.07
     Control
    -0.06
    .Criteria
    -0.06
     Poe
    -0.06
     schnell
    -0.06
    errar
    -0.06
    .Cancel
    -0.06
    	mem
    -0.06
    Top
    -0.06
    POSITIVE LOGITS
    here
    0.06
    нообраз
    0.06
    ulf
    0.06
    .spi
    0.06
    奴
    0.06
    alted
    0.06
     už
    0.06
     prizes
    0.06
    ΥΣ
    0.06
    coverage
    0.06
    Act Density 0.024%

    No Known Activations