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

    Neuronpedia

    INDEX
    Explanations

    predict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bar
    -0.07
     essere
    -0.06
     um
    -0.06
    AND
    -0.06
     island
    -0.06
    ungeon
    -0.06
     crowds
    -0.06
     trị
    -0.06
    Judge
    -0.06
    ิการ
    -0.06
    POSITIVE LOGITS
     abbrev
    0.08
     unfore
    0.07
    ・・・
    0.07
     ngăn
    0.06
     journalistic
    0.06
     Mits
    0.06
     tráv
    0.06
    があり
    0.06
     Bryce
    0.06
    Sports
    0.06
    Act Density 0.008%

    No Known Activations