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

    Neuronpedia

    INDEX
    Explanations

    apostrophes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     you
    -0.08
     Slo
    -0.07
    ,readonly
    -0.07
     считается
    -0.07
     sandbox
    -0.07
     we
    -0.07
     Sky
    -0.06
     sept
    -0.06
     You
    -0.06
    velocity
    -0.06
    POSITIVE LOGITS
    122
    0.06
    .CustomButton
    0.06
     投稿日
    0.06
    DES
    0.06
     Leipzig
    0.06
     poté
    0.06
    //=
    0.06
     双线
    0.06
    TERN
    0.06
    ']):↵
    0.06
    Act Density 0.015%

    No Known Activations