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

    Neuronpedia

    INDEX
    Explanations

    right

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -pe
    -0.07
    -slider
    -0.07
    /GPL
    -0.06
    /interface
    -0.06
    Tuesday
    -0.06
    DVD
    -0.06
     casos
    -0.06
     weekly
    -0.06
    atings
    -0.06
    	TEST
    -0.06
    POSITIVE LOGITS
     cats
    0.07
    	com
    0.07
     expectedResult
    0.07
    ρες
    0.06
     allev
    0.06
     aber
    0.06
    (callback
    0.06
    ğinin
    0.06
     společnosti
    0.06
    (cb
    0.06
    Act Density 0.010%

    No Known Activations