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

    Neuronpedia

    INDEX
    Explanations

    esc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Aw
    -0.06
    .RestController
    -0.06
    .uri
    -0.06
    يد
    -0.06
    irate
    -0.06
    _ur
    -0.06
     RequestMethod
    -0.06
    ünkü
    -0.06
     Aw
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     mutation
    0.08
     ráno
    0.07
     twice
    0.07
     leave
    0.07
     naive
    0.07
     divor
    0.07
    ii
    0.07
     sparse
    0.07
     adjustments
    0.07
     wholly
    0.07
    Act Density 0.000%

    No Known Activations