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

    Neuronpedia

    INDEX
    Explanations

    Speaking/expressing oneself

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ین
    -0.07
     translateY
    -0.07
    cxx
    -0.07
    ậy
    -0.07
    	then
    -0.06
    -su
    -0.06
    )sender
    -0.06
     mín
    -0.06
    ста
    -0.06
    ╗
    -0.06
    POSITIVE LOGITS
    stract
    0.06
    (sess
    0.06
     Summers
    0.06
    MESSAGE
    0.06
    isser
    0.06
    -static
    0.06
    γων
    0.06
    �
    0.06
    /Observable
    0.06
    (expect
    0.06
    Act Density 0.304%

    No Known Activations