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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    筻
    -0.07
    壕
    -0.07
     bars
    -0.07
     BEL
    -0.07
    Minor
    -0.07
     sponsor
    -0.07
    갹
    -0.07
    心脏
    -0.07
    刘海
    -0.07
    _indicator
    -0.07
    POSITIVE LOGITS
     дем
    0.07
    โปรแกรม
    0.07
    楼层
    0.07
    ⽬
    0.06
     exporting
    0.06
     pts
    0.06
     Keith
    0.06
    policy
    0.06
    ǣ
    0.06
     עבודה
    0.06
    Act Density 0.003%

    No Known Activations