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

    Neuronpedia

    INDEX
    Explanations

    studies or assessments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dumpster
    -0.07
     raided
    -0.07
     pudding
    -0.07
     ;)↵↵
    -0.06
     comando
    -0.06
     asserted
    -0.06
     raids
    -0.06
    到的
    -0.06
    ：「
    -0.06
    mys
    -0.06
    POSITIVE LOGITS
    ्यवस
    0.06
    NDER
    0.06
    .GetName
    0.06
    utors
    0.06
    ANDLE
    0.06
    onical
    0.06
     와
    0.06
    quiring
    0.06
     gerek
    0.06
     अव
    0.05
    Act Density 0.037%

    No Known Activations