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

    Neuronpedia

    INDEX
    Explanations

    Code and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     краще
    -0.06
     welche
    -0.06
     tylko
    -0.06
    �
    -0.06
    emales
    -0.06
     उपलब
    -0.06
     wiki
    -0.06
     WWE
    -0.06
     yOffset
    -0.06
    ‌کنند
    -0.06
    POSITIVE LOGITS
     Lever
    0.08
    BED
    0.07
     discord
    0.07
     reductions
    0.07
    /dr
    0.06
    (packet
    0.06
     Allocation
    0.06
    499
    0.06
    istol
    0.06
     educ
    0.06
    Act Density 0.000%

    No Known Activations