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

    Neuronpedia

    INDEX
    Explanations

    hard disk read/write head

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -actions
    -0.08
     EO
    -0.07
    .all
    -0.07
     princes
    -0.07
    انخفاض
    -0.07
    Range
    -0.07
    完备
    -0.07
    リア
    -0.07
    quisites
    -0.07
    .Vector
    -0.07
    POSITIVE LOGITS
     nhờ
    0.07
    يمي
    0.07
     important
    0.07
     Shotgun
    0.06
     potato
    0.06
     respecto
    0.06
    opi
    0.06
    瑛
    0.06
    rb
    0.06
    %m
    0.06
    Act Density 0.028%

    No Known Activations