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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    箨
    -0.07
    ․
    -0.07
    "/></
    -0.07
    .pkg
    -0.07
    .bpm
    -0.07
     ignition
    -0.06
     buiten
    -0.06
    Clazz
    -0.06
    负责同志
    -0.06
    𝓿
    -0.06
    POSITIVE LOGITS
    瓮
    0.07
     incub
    0.07
    уль
    0.07
    acco
    0.07
     לרכ
    0.07
    бой
    0.07
    精品
    0.07
    餐
    0.07
    Freedom
    0.06
    ᛂ
    0.06
    Act Density 0.006%

    No Known Activations