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

    Neuronpedia

    INDEX
    Explanations

    PHP code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    neider
    -0.08
    うち
    -0.06
    orry
    -0.06
     engineers
    -0.06
     opting
    -0.06
    asons
    -0.06
    ็อต
    -0.06
    Ax
    -0.06
    amate
    -0.06
    cus
    -0.06
    POSITIVE LOGITS
     �
    0.06
    albums
    0.06
    	base
    0.06
     '*',
    0.06
    	glm
    0.06
    _MSB
    0.06
    _ssh
    0.06
     شعر
    0.06
     област
    0.06
    _image
    0.06
    Act Density 0.017%

    No Known Activations