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

    Neuronpedia

    INDEX
    Explanations

    location references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    peak
    -0.07
    nv
    -0.06
     MMM
    -0.06
    /player
    -0.06
    賀
    -0.06
    وه
    -0.06
    رده
    -0.06
    enler
    -0.06
    ']").
    -0.06
    men
    -0.06
    POSITIVE LOGITS
     Atlantic
    0.07
    plementation
    0.06
    .card
    0.06
    -append
    0.06
     такая
    0.06
    /validation
    0.06
     incident
    0.06
    Blake
    0.06
     yielded
    0.06
    /edit
    0.06
    Act Density 0.001%

    No Known Activations