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

    Neuronpedia

    INDEX
    Explanations

    Code/structured data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     йому
    -0.07
     Ně
    -0.06
    _fake
    -0.06
    NES
    -0.06
     �
    -0.06
    -Ray
    -0.06
     oversees
    -0.06
     witnessed
    -0.06
    変
    -0.06
     irres
    -0.06
    POSITIVE LOGITS
    �i
    0.06
     trav
    0.06
    endars
    0.06
    рок
    0.06
     fern
    0.06
     Každ
    0.06
    .
↵
↵
    0.06
     erotisch
    0.06
     actually
    0.06
     Mir
    0.06
    Act Density 0.001%

    No Known Activations