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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tak
    -0.06
     Tells
    -0.06
     reservation
    -0.06
     reasoning
    -0.06
     kor
    -0.06
     Bu
    -0.06
     Star
    -0.06
    ilebilir
    -0.06
    Strip
    -0.06
     Sun
    -0.06
    POSITIVE LOGITS
     //----------------------------------------------------------------
    0.07
    MATRIX
    0.06
    ้าร
    0.06
    atabase
    0.06
    airo
    0.06
     ÜNİVERS
    0.06
    ัญช
    0.06
    <?↵
    0.06
    localctx
    0.06
    ‌انبار
    0.06
    Act Density 0.000%

    No Known Activations