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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	ret
    -0.07
     Aeros
    -0.07
     domina
    -0.06
     trạng
    -0.06
     Foam
    -0.06
    	port
    -0.06
     reh
    -0.06
     Release
    -0.06
    _ff
    -0.06
    �y
    -0.06
    POSITIVE LOGITS
    .jar
    0.07
     guarding
    0.07
    .createObject
    0.07
    .pos
    0.06
    EMAIL
    0.06
     배송
    0.06
     salmon
    0.06
    .columns
    0.06
    quierda
    0.06
     vůči
    0.06
    Act Density 0.000%

    No Known Activations