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

    Neuronpedia

    INDEX
    Explanations

    exceptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    css
    -0.07
     defence
    -0.06
     місця
    -0.06
    compass
    -0.06
     texts
    -0.06
    ested
    -0.06
    tile
    -0.06
    jos
    -0.06
    .df
    -0.06
     handbook
    -0.06
    POSITIVE LOGITS
     ανά
    0.07
     Mü
    0.07
    .
    0.06
    ่างประเทศ
    0.06
    豆
    0.06
     ∨
    0.06
     authenticate
    0.06
    τρα
    0.06
     decipher
    0.06
     PX
    0.06
    Act Density 0.000%

    No Known Activations