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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    卒
    -0.07
     技
    -0.07
     Marines
    -0.07
    >To
    -0.06
     errorThrown
    -0.06
    ेख
    -0.06
     Atlas
    -0.06
     Nội
    -0.06
     Infer
    -0.06
     VIS
    -0.06
    POSITIVE LOGITS
    ayed
    0.07
    cmc
    0.07
     hlavu
    0.06
    enler
    0.06
    ANNEL
    0.06
     buggy
    0.06
     Fem
    0.06
    Directory
    0.06
    838
    0.06
    hur
    0.06
    Act Density 0.000%

    No Known Activations