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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ankles
    -0.07
     برد
    -0.06
    Z
    -0.06
     rents
    -0.06
     containers
    -0.06
    692
    -0.06
     Ngân
    -0.06
     incididunt
    -0.06
    ênh
    -0.06
    His
    -0.06
    POSITIVE LOGITS
     nuis
    0.07
    veyor
    0.06
     『
    0.06
    _standard
    0.06
     celé
    0.06
     سرمایه
    0.06
    や
    0.06
    альну
    0.06
    ())));↵
    0.06
     $__
    0.06
    Act Density 0.022%

    No Known Activations