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

    Neuronpedia

    INDEX
    Explanations

    ative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ませ
    -0.07
     chết
    -0.06
     estamos
    -0.06
    ’m
    -0.06
    -ad
    -0.06
    學校
    -0.06
     søger
    -0.06
     دش
    -0.06
    'm
    -0.06
    //------------------------------------------------------------------------------↵↵
    -0.06
    POSITIVE LOGITS
    .blogspot
    0.06
     interruption
    0.06
     动
    0.06
     jedné
    0.06
    (rng
    0.06
    کس
    0.06
    (sel
    0.06
    icism
    0.06
    quarters
    0.06
    记录
    0.06
    Act Density 0.002%

    No Known Activations