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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     עמוק
    -0.08
    ╛
    -0.07
    轻松
    -0.07
    weak
    -0.07
    西路
    -0.07
     bust
    -0.07
    rin
    -0.06
     Reve
    -0.06
     Riv
    -0.06
    unted
    -0.06
    POSITIVE LOGITS
    (character
    0.08
    (char
    0.07
    -phase
    0.07
    (nav
    0.07
    (chart
    0.07
     حاج
    0.07
     לשמור
    0.07
     Scratch
    0.06
    .nz
    0.06
    ሺ
    0.06
    Act Density 0.002%

    No Known Activations