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

    Neuronpedia

    INDEX
    Explanations

    forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FUNCTION
    -0.07
    ційна
    -0.07
    POSITION
    -0.06
    žení
    -0.06
     IX
    -0.06
     Polly
    -0.06
     Signs
    -0.06
     Svg
    -0.06
     [%
    -0.06
    ап
    -0.06
    POSITIVE LOGITS
    tsky
    0.07
    _Save
    0.07
    (recipe
    0.06
    arten
    0.06
     Jews
    0.06
     rarely
    0.06
    Vent
    0.06
     Stripe
    0.06
     Ekim
    0.06
    ندا
    0.06
    Act Density 0.006%

    No Known Activations