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

    Neuronpedia

    INDEX
    Explanations

    image

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вас
    -0.08
    .setPrototypeOf
    -0.08
    ♁
    -0.07
    .blocks
    -0.07
    	o
    -0.07
     /↵
    -0.07
    @PostMapping
    -0.07
    út
    -0.07
    Hola
    -0.07
    .Driver
    -0.07
    POSITIVE LOGITS
    chia
    0.07
    _MACHINE
    0.07
    合适
    0.06
     Murray
    0.06
    `,
    0.06
    꿔
    0.06
     Compliance
    0.06
    bb
    0.06
    水产
    0.06
    뺘
    0.06
    Act Density 0.002%

    No Known Activations