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

    Neuronpedia

    INDEX
    Explanations

    therefore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .accel
    -0.07
    -0.07
    .Args
    -0.07
    .inverse
    -0.07
    unta
    -0.06
     tightly
    -0.06
     ------------------------------------------------------------------------↵
    -0.06
     trends
    -0.06
     день
    -0.06
    .L
    -0.06
    POSITIVE LOGITS
    fdf
    0.07
     esports
    0.07
     ilg
    0.06
     Eleanor
    0.06
    them
    0.06
     borrowing
    0.06
     επι
    0.06
     pretending
    0.06
     nå
    0.06
     Pending
    0.06
    Act Density 0.828%

    No Known Activations