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

    Neuronpedia

    INDEX
    Explanations

    literary texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eva
    -0.06
    StrLn
    -0.06
    Cl
    -0.06
    >()↵↵
    -0.06
     Luk
    -0.06
     requ
    -0.06
     organism
    -0.06
    義
    -0.06
    젠
    -0.06
     freshness
    -0.06
    POSITIVE LOGITS
    _part
    0.07
     sincere
    0.07
    /////
    0.06
    tej
    0.06
    //[
    0.06
     Vox
    0.06
    اجات
    0.06
    _press
    0.06
     Last
    0.06
    WithTitle
    0.06
    Act Density 0.001%

    No Known Activations