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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vibrant
    -0.08
     Jefferson
    -0.08
    ૌ
    -0.08
     вр
    -0.07
     verir
    -0.07
     तौर
    -0.07
     querying
    -0.07
     મુદ્દ
    -0.07
     hub
    -0.07
     jaz
    -0.07
    POSITIVE LOGITS
     организме
    0.09
     составе
    0.09
     motorway
    0.08
     compositions
    0.08
     petrol
    0.08
     samenleving
    0.08
     rámci
    0.08
     рынке
    0.08
     repay
    0.07
    退出
    0.07
    Act Density 0.012%

    No Known Activations