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

    Neuronpedia

    INDEX
    Explanations

    Put

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .fit
    -0.07
     porówn
    -0.07
    uters
    -0.07
     OnePlus
    -0.07
    Dallas
    -0.07
    _human
    -0.07
    汩
    -0.07
    蠕
    -0.07
     bfd
    -0.07
    跆
    -0.07
    POSITIVE LOGITS
     redemption
    0.07
    (program
    0.07
    保持着
    0.06
    京
    0.06
    햔
    0.06
    皇帝
    0.06
    edral
    0.06
    pector
    0.06
    RestController
    0.06
     такой
    0.06
    Act Density 0.002%

    No Known Activations