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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verbosity
    -0.07
     dil
    -0.06
     withdrawing
    -0.06
     immobil
    -0.06
     布
    -0.06
    ä
    -0.06
    (Window
    -0.06
    adelphia
    -0.06
     mobility
    -0.06
    OP
    -0.06
    POSITIVE LOGITS
    _price
    0.06
    Todos
    0.06
    resolve
    0.06
     Powerful
    0.06
    obsolete
    0.06
    .')↵
    0.06
    Contains
    0.06
    Snake
    0.06
     🙂↵↵
    0.06
     ]↵
    0.06
    Act Density 0.024%

    No Known Activations