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

    Neuronpedia

    INDEX
    Explanations

    reservations and confirmations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    府
    -0.06
    _structure
    -0.06
    GENCY
    -0.06
    .Transform
    -0.06
     Homeland
    -0.06
     adaptations
    -0.06
     Defense
    -0.06
     foes
    -0.06
     necessity
    -0.06
    Calibri
    -0.06
    POSITIVE LOGITS
     yt
    0.07
     Vince
    0.06
     Nash
    0.06
    (agent
    0.06
     Eisen
    0.06
     Washer
    0.06
     Mitgli
    0.06
     어떤
    0.06
    _emb
    0.06
    ıştır
    0.06
    Act Density 0.020%

    No Known Activations