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

    Neuronpedia

    INDEX
    Explanations

    Neural networks code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Healing
    -0.08
     perpetual
    -0.08
     vane
    -0.07
     Orthodox
    -0.07
     procura
    -0.07
     balm
    -0.07
     kittens
    -0.07
     espagn
    -0.07
    Healing
    -0.07
     healing
    -0.07
    POSITIVE LOGITS
    (Dense
    0.12
     logits
    0.09
    (bottom
    0.09
     Dense
    0.09
     Smash
    0.09
    connect
    0.09
     conectado
    0.08
    ท้าย
    0.08
     puro
    0.08
    .dropout
    0.08
    Act Density 0.004%

    No Known Activations