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

    Neuronpedia

    INDEX
    Explanations

    public announcements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foo
    -0.07
    Transport
    -0.06
     ruce
    -0.06
     Kč
    -0.06
    เตร
    -0.06
     ethernet
    -0.06
     semen
    -0.06
     beige
    -0.06
    PLIC
    -0.06
     oben
    -0.06
    POSITIVE LOGITS
    보다
    0.07
     ha
    0.07
     climbs
    0.06
     demonstration
    0.06
     Sinclair
    0.06
     BUFF
    0.06
     Relatives
    0.06
    lay
    0.06
    likler
    0.06
    =image
    0.06
    Act Density 0.021%

    No Known Activations