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

    Neuronpedia

    INDEX
    Explanations

    display

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transformation
    -0.07
    DX
    -0.07
    .Wait
    -0.06
    ,input
    -0.06
     expression
    -0.06
     win
    -0.06
    _random
    -0.06
    üstü
    -0.06
    Elf
    -0.06
     exchange
    -0.06
    POSITIVE LOGITS
     taille
    0.06
     peeled
    0.06
     biển
    0.06
     вполне
    0.06
        
    0.06
     Opp
    0.06
    Transparent
    0.06
     �
    0.06
    �
    0.06
    홍
    0.06
    Act Density 0.010%

    No Known Activations