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

    Neuronpedia

    INDEX
    Explanations

    concerned,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    隠
    -0.06
     Beverly
    -0.06
     도시
    -0.06
     Й
    -0.05
    paralleled
    -0.05
     Буд
    -0.05
     Wor
    -0.05
     Memories
    -0.05
    %C
    -0.05
    	fill
    -0.05
    POSITIVE LOGITS
     exercising
    0.07
    :A
    0.07
    .setOutput
    0.07
    μβρίου
    0.07
    ीव
    0.07
     Δ
    0.06
     forward
    0.06
     cyclic
    0.06
     leuk
    0.06
    InOut
    0.06
    Act Density 0.054%

    No Known Activations