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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    388
    -0.07
     але
    -0.07
     мне
    -0.06
    介绍
    -0.06
    529
    -0.06
    .quantity
    -0.06
     elements
    -0.06
     en
    -0.06
     wij
    -0.06
    duit
    -0.06
    POSITIVE LOGITS
    onor
    0.08
    ov
    0.08
    ove
    0.07
    ox
    0.07
     noct
    0.07
    ようです
    0.07
    OX
    0.07
    онов
    0.07
    erview
    0.07
    OV
    0.07
    Act Density 0.030%

    No Known Activations