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

    Neuronpedia

    INDEX
    Explanations

    align

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    绵
    -0.08
    _spinner
    -0.07
    IGGER
    -0.07
     Apartment
    -0.07
     Advantage
    -0.07
     Sellers
    -0.07
    Circular
    -0.07
     bulun
    -0.07
     Country
    -0.07
    𬜬
    -0.06
    POSITIVE LOGITS
    adoo
    0.07
    ฤษ
    0.07
     clientele
    0.07
    日军
    0.07
    当事人
    0.06
    AccessToken
    0.06
     bada
    0.06
    ضاء
    0.06
     Goku
    0.06
     dokładnie
    0.06
    Act Density 0.011%

    No Known Activations