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

    Neuronpedia

    INDEX
    Explanations

    massive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spontaneously
    -0.07
     bt
    -0.07
    研讨会
    -0.07
    ulate
    -0.07
     Blanc
    -0.07
     ضمن
    -0.07
     Brown
    -0.07
     density
    -0.07
     bunk
    -0.07
     engineers
    -0.06
    POSITIVE LOGITS
     Tried
    0.07
    (Process
    0.07
     Death
    0.07
    喉
    0.07
     orderly
    0.07
     Entities
    0.07
    𝗢
    0.07
    /@
    0.07
    stackpath
    0.07
    GetObject
    0.06
    Act Density 0.132%

    No Known Activations