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

    Neuronpedia

    INDEX
    Explanations

    code and file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    社区
    -0.07
     jr
    -0.07
     punished
    -0.07
    (header
    -0.06
    walking
    -0.06
     Kag
    -0.06
    .shadow
    -0.06
     HIT
    -0.06
     Maryland
    -0.06
    aza
    -0.06
    POSITIVE LOGITS
    usk
    0.06
    æk
    0.06
     Čech
    0.06
     morph
    0.06
    eacher
    0.06
     disregard
    0.06
    -helper
    0.06
    ПК
    0.06
     delight
    0.06
    emand
    0.06
    Act Density 0.223%

    No Known Activations