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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     onion
    -0.06
    .p
    -0.06
     merger
    -0.06
     analytics
    -0.06
    _Per
    -0.06
    met
    -0.06
     onions
    -0.06
    иц
    -0.06
    -pencil
    -0.06
    RIA
    -0.06
    POSITIVE LOGITS
    INSTANCE
    0.07
    }')
    0.06
     priceless
    0.06
    “,
    0.06
     گرف
    0.06
     totalPages
    0.06
    xfb
    0.06
    μένου
    0.06
     ){
    0.06
    отя
    0.06
    Act Density 0.021%

    No Known Activations