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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    XmlAccessorType
    -0.84
    новниш
    -0.73
    PerformLayout
    -0.70
    verwijspagina
    -0.69
     censiti
    -0.69
    >>>>>>>
    -0.68
    rawDesc
    -0.67
    twimg
    -0.66
     TextInputType
    -0.66
    SharedDtor
    -0.66
    POSITIVE LOGITS
     course
    0.64
     path
    0.59
     progress
    0.54
     flow
    0.53
     growth
    0.51
     rise
    0.50
     movement
    0.50
     route
    0.49
     use
    0.48
    ocytosis
    0.48
    Act Density 0.009%

    No Known Activations