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

    Neuronpedia

    INDEX
    Explanations

    missed opportunities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vertex
    -0.07
    (concat
    -0.06
    Hu
    -0.06
    �
    -0.06
    __
↵
    -0.06
     facade
    -0.06
    แล
    -0.06
    elerden
    -0.06
    医学
    -0.06
     επί
    -0.06
    POSITIVE LOGITS
    Civil
    0.07
     Ind
    0.06
    ithe
    0.06
     сила
    0.06
     reversed
    0.06
     Pol
    0.06
    und
    0.06
    .writeInt
    0.06
    eight
    0.06
     THB
    0.06
    Act Density 0.013%

    No Known Activations