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

    Neuronpedia

    INDEX
    Explanations

    numbers in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	body
    -0.07
    Angles
    -0.07
    oty
    -0.07
     partager
    -0.07
     screws
    -0.07
     cal
    -0.06
     listar
    -0.06
     card
    -0.06
     sensors
    -0.06
    اين
    -0.06
    POSITIVE LOGITS
    京
    0.06
    �
    0.06
     BYTE
    0.06
    ��
    0.06
    xEA
    0.06
     �
    0.06
    -gallery
    0.06
    лаб
    0.06
    .Note
    0.06
     σχ
    0.06
    Act Density 0.008%

    No Known Activations