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

    Neuronpedia

    INDEX
    Explanations

    lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Players
    -0.07
    _Name
    -0.06
    acho
    -0.06
     आख
    -0.06
     вра
    -0.06
    ;padding
    -0.06
    .song
    -0.06
    .OR
    -0.06
    структор
    -0.06
    .File
    -0.06
    POSITIVE LOGITS
     Manafort
    0.07
    ají
    0.06
     Attribute
    0.06
     Valerie
    0.06
     ib
    0.06
    				
↵
    0.06
    られた
    0.06
    íž
    0.06
    	texture
    0.06
    ]]];↵
    0.06
    Act Density 0.021%

    No Known Activations