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

    Neuronpedia

    INDEX
    Explanations

    riddles and puzzles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Một
    -0.10
     Extr
    -0.08
     glitter
    -0.07
    stä
    -0.07
    ハイ
    -0.07
     Mental
    -0.07
    ADMIN
    -0.07
    minster
    -0.07
     hormone
    -0.07
     Site
    -0.07
    POSITIVE LOGITS
    .RowCount
    0.08
    обща
    0.07
     sonras
    0.07
    .currentState
    0.07
    ゃ
    0.07
    ATIONS
    0.07
    =N
    0.07
    paration
    0.07
    让它
    0.06
    即
    0.06
    Act Density 0.011%

    No Known Activations