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

    Neuronpedia

    INDEX
    Explanations

    complex sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     two
    -0.06
    ekil
    -0.06
     cihaz
    -0.06
     hedge
    -0.06
    нист
    -0.06
     середови
    -0.06
     OL
    -0.06
     old
    -0.06
     carga
    -0.06
     three
    -0.06
    POSITIVE LOGITS
    .neighbors
    0.07
    わたし
    0.07
    ापक
    0.06
    ptune
    0.06
     RTWF
    0.06
     enticing
    0.06
     anyway
    0.06
    　ヾ
    0.06
     onward
    0.06
    -document
    0.06
    Act Density 0.000%

    No Known Activations