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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     generar
    -0.07
     spolupráci
    -0.06
     thrott
    -0.06
     plutôt
    -0.06
     přím
    -0.06
    tight
    -0.06
     Stat
    -0.06
    bia
    -0.06
     приня
    -0.06
     steadily
    -0.06
    POSITIVE LOGITS
     QB
    0.07
    ASHINGTON
    0.07
    ;n
    0.07
     yerini
    0.06
    _numeric
    0.06
    az
    0.06
    CharacterSet
    0.06
    ehler
    0.06
    etermine
    0.06
    しまった
    0.06
    Act Density 0.013%

    No Known Activations