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

    Neuronpedia

    INDEX
    Explanations

    Theatrical performances

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    后
    -0.07
     این
    -0.06
    电话
    -0.06
     улыб
    -0.06
     υπ
    -0.06
     Blackhawks
    -0.06
     Tes
    -0.06
     trẻ
    -0.06
    Chooser
    -0.06
     typing
    -0.06
    POSITIVE LOGITS
     Mandatory
    0.07
     Canadian
    0.07
    ellant
    0.07
     excellent
    0.07
    égor
    0.07
     Short
    0.06
    pis
    0.06
    cing
    0.06
     hunted
    0.06
     Наг
    0.06
    Act Density 0.063%

    No Known Activations