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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tweak
    -0.07
    ないです
    -0.07
    /the
    -0.07
    duino
    -0.07
    lıkları
    -0.07
    ęki
    -0.06
    쑈
    -0.06
    świadczenie
    -0.06
    댸
    -0.06
    שוקולד
    -0.06
    POSITIVE LOGITS
    %p
    0.08
    攝
    0.08
    ա
    0.07
    uc
    0.07
     Pal
    0.07
     imp
    0.07
     hexatrigesimal
    0.07
     seven
    0.07
     angles
    0.07
     perfect
    0.07
    Act Density 0.185%

    No Known Activations