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

    Neuronpedia

    INDEX
    Explanations

    Taking away

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     موسی
    -0.09
    ानी
    -0.09
    사진
    -0.08
    announcement
    -0.08
    Announcement
    -0.08
     musica
    -0.08
     audiovisual
    -0.08
    TACT
    -0.08
     smack
    -0.08
     Tac
    -0.08
    POSITIVE LOGITS
     Reduction
    0.09
     cuota
    0.09
     reduction
    0.09
    吞
    0.09
     entrants
    0.08
     releg
    0.08
     ઘટાડ
    0.08
     underserved
    0.08
     realloc
    0.08
     redistribute
    0.08
    Act Density 0.029%

    No Known Activations