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

    Neuronpedia

    INDEX
    Explanations

    Concern

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Brittany
    -0.08
     шаг
    -0.08
    влаж
    -0.07
     "--
    -0.07
     requestOptions
    -0.07
    .lists
    -0.07
     eta
    -0.07
     ¡
    -0.07
     pups
    -0.07
     whipped
    -0.07
    POSITIVE LOGITS
    햠
    0.08
    dz
    0.08
     concerning
    0.07
     corresponds
    0.07
     concerned
    0.07
    烜
    0.07
    .permissions
    0.07
     concerns
    0.07
     EXPER
    0.06
    _QUAL
    0.06
    Act Density 0.018%

    No Known Activations