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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LEN
    -0.07
    里面的
    -0.07
     Tek
    -0.07
     Coleman
    -0.07
    Ts
    -0.07
    也有很多
    -0.07
     piles
    -0.07
    Draft
    -0.07
    侹
    -0.07
    (android
    -0.07
    POSITIVE LOGITS
     @_
    0.07
     warrior
    0.07
    ":""
    0.07
     ситу
    0.07
    اش
    0.06
    对我说
    0.06
    🏗
    0.06
    ปฏ
    0.06
     Hate
    0.06
     Goes
    0.06
    Act Density 0.019%

    No Known Activations