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

    Neuronpedia

    INDEX
    Explanations

    classical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("================
    -0.08
     పడ
    -0.08
    Algorithm
    -0.07
    Which
    -0.07
    Let
    -0.07
    (),
    -0.07
     which
    -0.07
    Quick
    -0.07
     которая
    -0.07
     __________
    -0.07
    POSITIVE LOGITS
     lesen
    0.09
    閱讀
    0.08
    资料
    0.08
     жизни
    0.08
    yllic
    0.08
     conception
    0.08
     unnoticed
    0.08
    ationen
    0.08
    èy
    0.08
     präsent
    0.08
    Act Density 0.006%

    No Known Activations