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

    Neuronpedia

    INDEX
    Explanations

    inal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     являются
    -0.07
    vided
    -0.07
    -than
    -0.07
    您的
    -0.06
    ními
    -0.06
    =""><
    -0.06
     tượng
    -0.06
    bruary
    -0.06
     meiner
    -0.06
     считается
    -0.06
    POSITIVE LOGITS
     Monroe
    0.07
     Sanat
    0.07
    Shortcut
    0.07
     куб
    0.06
     hashMap
    0.06
     carousel
    0.06
    getService
    0.06
    ková
    0.06
     Dirk
    0.06
     floor
    0.06
    Act Density 0.000%

    No Known Activations