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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    娜
    -0.06
    绍
    -0.06
     Mon
    -0.06
     Triumph
    -0.06
     sharks
    -0.06
     Womens
    -0.06
     Fab
    -0.06
    蘇
    -0.05
    磨
    -0.05
     jer
    -0.05
    POSITIVE LOGITS
     COURT
    0.07
    ainties
    0.07
    (baseUrl
    0.07
    689
    0.07
    326
    0.07
     RESET
    0.07
    creat
    0.06
    -log
    0.06
    previous
    0.06
    ständ
    0.06
    Act Density 0.001%

    No Known Activations