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

    Neuronpedia

    INDEX
    Explanations

    marginal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    棰
    -0.07
    锡
    -0.07
     Chef
    -0.07
     Hitler
    -0.07
    )((((
    -0.07
    _BUF
    -0.06
    海拔
    -0.06
    .defer
    -0.06
     Ri
    -0.06
     ess
    -0.06
    POSITIVE LOGITS
     marginal
    0.08
    监护
    0.07
     يقول
    0.07
     indic
    0.07
    ималь
    0.06
     قائلا
    0.06
    ätze
    0.06
    ⛸
    0.06
    xima
    0.06
     treeNode
    0.06
    Act Density 0.003%

    No Known Activations