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

    Neuronpedia

    INDEX
    Explanations

    投

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    string
    -0.07
    /misc
    -0.06
    struction
    -0.06
     Commerce
    -0.06
    ция
    -0.06
     transporte
    -0.06
    íveis
    -0.06
    爽
    -0.06
     expectation
    -0.06
     Memories
    -0.06
    POSITIVE LOGITS
     PROF
    0.07
    汽
    0.07
    (not
    0.07
     خیلی
    0.06
     투
    0.06
     입니다
    0.06
     Sabb
    0.06
     pared
    0.06
     Gur
    0.06
    filtr
    0.06
    Act Density 0.004%

    No Known Activations