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

    Neuronpedia

    INDEX
    Explanations

    clone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lord
    -0.07
    ानत
    -0.06
    こそ
    -0.06
     сіль
    -0.06
    .GroupLayout
    -0.06
    .heading
    -0.06
     sauce
    -0.06
     emit
    -0.06
    gp
    -0.06
    ским
    -0.06
    POSITIVE LOGITS
     Pokémon
    0.07
     dictates
    0.06
     Hermes
    0.06
     LINK
    0.06
     руч
    0.06
     userDao
    0.06
     kidding
    0.06
    READY
    0.06
     shortcut
    0.06
    ади
    0.06
    Act Density 0.005%

    No Known Activations