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

    Neuronpedia

    INDEX
    Explanations

    check

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .IsMatch
    -0.07
     calculations
    -0.07
    Rp
    -0.07
     rotated
    -0.07
    Gravity
    -0.06
     rubbed
    -0.06
     Transparent
    -0.06
     Бі
    -0.06
    ा)
    -0.06
     Brittany
    -0.06
    POSITIVE LOGITS
     wl
    0.06
     mates
    0.06
    _intf
    0.06
    plus
    0.06
     interior
    0.06
    uger
    0.06
     hentai
    0.06
     sponsored
    0.06
    हन
    0.06
     disqualified
    0.06
    Act Density 0.006%

    No Known Activations