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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بندی
    -0.07
    яч
    -0.07
     banc
    -0.07
    imuth
    -0.07
    /npm
    -0.07
    伯
    -0.07
     пищ
    -0.06
    ubber
    -0.06
    еров
    -0.06
    .guild
    -0.06
    POSITIVE LOGITS
     Monte
    0.07
     National
    0.07
    Intern
    0.07
     Annual
    0.06
    Vol
    0.06
     Bengal
    0.06
    (filtered
    0.06
     augmented
    0.06
    hud
    0.06
     annual
    0.06
    Act Density 0.000%

    No Known Activations