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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Invoke
    -0.07
    #get
    -0.07
    zac
    -0.07
    [np
    -0.07
    unwrap
    -0.06
     {?}
    -0.06
     DSM
    -0.06
    essages
    -0.06
     Symptoms
    -0.06
    Arm
    -0.06
    POSITIVE LOGITS
    ผล
    0.06
     Grades
    0.06
     graduation
    0.06
     düşün
    0.06
    istra
    0.06
     Minneapolis
    0.06
    operate
    0.06
     고
    0.06
     UserRole
    0.06
    ifers
    0.06
    Act Density 0.010%

    No Known Activations