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

    Neuronpedia

    INDEX
    Explanations

    evaluate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [max
    -0.06
    struk
    -0.06
    (old
    -0.06
    setMax
    -0.06
    τικα
    -0.06
    ीक
    -0.06
    едини
    -0.06
     hombres
    -0.06
    洋
    -0.06
     Kota
    -0.06
    POSITIVE LOGITS
    call
    0.07
    Submit
    0.07
     power
    0.07
    ίνεται
    0.07
     عفش
    0.07
     Evan
    0.06
    Attend
    0.06
    Digital
    0.06
     Calls
    0.06
    ETA
    0.06
    Act Density 0.005%

    No Known Activations