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

    Neuronpedia

    INDEX
    Explanations

    say the ending -ities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Machine
    -0.07
     ((!
    -0.07
     sorting
    -0.07
     summed
    -0.06
    ست
    -0.06
    olson
    -0.06
     hover
    -0.06
    睛
    -0.06
     vowels
    -0.06
    -ref
    -0.06
    POSITIVE LOGITS
     newfound
    0.06
     Reid
    0.06
    ěk
    0.06
    ulous
    0.06
     зміст
    0.06
    RAND
    0.06
    َح
    0.06
     본
    0.06
    คว
    0.06
     الاح
    0.06
    Act Density 0.002%

    No Known Activations