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

    Neuronpedia

    INDEX
    Explanations

    yards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     наличие
    -0.07
    tu
    -0.07
     联
    -0.06
     Kab
    -0.06
     cosa
    -0.06
    嫌
    -0.06
    aptor
    -0.06
    flat
    -0.06
     馬
    -0.06
     Ment
    -0.06
    POSITIVE LOGITS
    ("----------------
    0.06
     healthier
    0.06
     Leave
    0.06
    bursement
    0.06
    sey
    0.06
     thirteen
    0.06
     }));↵
    0.06
    ****************************************************************
    0.06
     comments
    0.06
    กรณ
    0.06
    Act Density 0.021%

    No Known Activations