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

    Neuronpedia

    INDEX
    Explanations

    der

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ediyor
    -0.07
    ापक
    -0.06
    -п
    -0.06
     ked
    -0.06
    립
    -0.06
    ازی
    -0.06
     उद
    -0.06
    の一
    -0.06
     Diploma
    -0.06
     biliyor
    -0.06
    POSITIVE LOGITS
     potrav
    0.07
     entertainment
    0.07
     pristine
    0.06
    issent
    0.06
     Sage
    0.06
    issor
    0.06
    äre
    0.06
    ewise
    0.06
    _consts
    0.06
     sucesso
    0.06
    Act Density 0.058%

    No Known Activations