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

    Neuronpedia

    INDEX
    Explanations

    lose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slun
    -0.07
     LTS
    -0.07
    介绍
    -0.06
    략
    -0.06
     intptr
    -0.06
     Onc
    -0.06
     xmax
    -0.06
    ketøy
    -0.06
     můž
    -0.06
    bw
    -0.06
    POSITIVE LOGITS
     кож
    0.07
    latesAutoresizingMaskIntoConstraints
    0.07
    commission
    0.06
     discern
    0.06
    ved
    0.06
     Worce
    0.06
    Apparently
    0.06
     somehow
    0.06
    ophe
    0.06
     Somehow
    0.06
    Act Density 0.016%

    No Known Activations