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

    Neuronpedia

    INDEX
    Explanations

    (withIdentifier

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    insula
    -0.07
     Audit
    -0.07
    廉
    -0.07
     paddingLeft
    -0.06
     spooky
    -0.06
     Thủ
    -0.06
     veniam
    -0.06
    ValueType
    -0.06
    宠
    -0.06
    .ico
    -0.06
    POSITIVE LOGITS
     switching
    0.07
     bordel
    0.07
    سقط
    0.07
     intens
    0.07
    放下
    0.07
    喋
    0.07
    seconds
    0.06
    ATCH
    0.06
     дней
    0.06
    (drop
    0.06
    Act Density 0.001%

    No Known Activations