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

    Neuronpedia

    INDEX
    Explanations

    reasoning and justification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consume
    -0.07
     reinforcing
    -0.07
     buffering
    -0.07
     vacations
    -0.06
    arge
    -0.06
     tour
    -0.06
    comment
    -0.06
     nghị
    -0.06
     Horde
    -0.06
     Mature
    -0.06
    POSITIVE LOGITS
     그러
    0.07
     používá
    0.07
    .wrapper
    0.07
     vaz
    0.06
     Між
    0.06
     whichever
    0.06
    最
    0.06
    uyordu
    0.06
    ΑΛ
    0.06
    .DisplayMember
    0.06
    Act Density 0.002%

    No Known Activations