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

    Neuronpedia

    INDEX
    Explanations

    No

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     squad
    -0.07
     Tet
    -0.07
     Toe
    -0.07
     Bron
    -0.07
    duino
    -0.06
    airie
    -0.06
    gz
    -0.06
    ileo
    -0.06
     blocked
    -0.06
     pumpkin
    -0.06
    POSITIVE LOGITS
     Beautiful
    0.07
    ันวาคม
    0.06
     علم
    0.06
    _PROVIDER
    0.06
     зовсім
    0.06
     Seeing
    0.06
     demeanor
    0.06
     بعضی
    0.06
     hindsight
    0.06
    ческая
    0.06
    Act Density 0.329%

    No Known Activations