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

    Neuronpedia

    INDEX
    Explanations

    code or AWS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    included
    -0.07
    _SO
    -0.06
    ㉡
    -0.06
     TAKE
    -0.06
    ᱚ
    -0.06
     uart
    -0.06
    帛
    -0.06
     BER
    -0.06
     Theo
    -0.06
    各有
    -0.06
    POSITIVE LOGITS
     topLeft
    0.08
    前十
    0.07
    луч
    0.07
    Subset
    0.07
    _hub
    0.07
     �
    0.07
     finalist
    0.07
     repositories
    0.07
     sanit
    0.07
     currentState
    0.07
    Act Density 0.092%

    No Known Activations