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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    駆
    -0.07
    ạng
    -0.07
    운데
    -0.07
    .cr
    -0.06
     уточ
    -0.06
     adjud
    -0.06
     airs
    -0.06
    660
    -0.06
    ोप
    -0.06
     행동
    -0.06
    POSITIVE LOGITS
     Bloomberg
    0.07
    　　 　 　 　 　
    0.07
     الميلاد
    0.06
     MULTI
    0.06
    Exited
    0.06
    _ORD
    0.06
    IPPING
    0.06
    iteur
    0.06
    ambiguous
    0.06
    loomberg
    0.06
    Act Density 0.220%

    No Known Activations