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

    Neuronpedia

    INDEX
    Explanations

    Last of its kind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mathematical
    -0.07
     Both
    -0.07
     П
    -0.07
    (re
    -0.07
    _week
    -0.07
    variables
    -0.07
     выб
    -0.07
     马
    -0.06
    _aw
    -0.06
     브라
    -0.06
    POSITIVE LOGITS
     Ethiopia
    0.07
    unker
    0.06
     quieres
    0.06
    PRECATED
    0.06
    shi
    0.06
     Candidates
    0.06
    _PWM
    0.06
    CANCEL
    0.06
    lásil
    0.06
     Washer
    0.05
    Act Density 0.000%

    No Known Activations