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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dungeon
    -0.08
    isinin
    -0.07
    aturdays
    -0.06
    eteor
    -0.06
    ZH
    -0.06
     температу
    -0.06
    oglobin
    -0.06
     ради
    -0.06
     الح
    -0.06
    /cache
    -0.06
    POSITIVE LOGITS
    (exports
    0.07
    gradation
    0.07
    855
    0.06
    isser
    0.06
    raises
    0.06
    ivor
    0.06
     unidad
    0.06
    诺
    0.06
    .writeHead
    0.06
     выс
    0.06
    Act Density 0.021%

    No Known Activations