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

    Neuronpedia

    INDEX
    Explanations

    Twilight Zone/Outer Limits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    раз
    -0.07
     cushion
    -0.06
     Tr
    -0.06
    ossa
    -0.06
     enquanto
    -0.06
    لاق
    -0.06
     curious
    -0.06
    同時
    -0.06
     continua
    -0.06
    虽然
    -0.06
    POSITIVE LOGITS
     rpm
    0.06
    .pretty
    0.06
    _aliases
    0.06
    ffe
    0.06
    "]."
    0.06
    боратор
    0.06
    .fail
    0.06
    맨
    0.06
    ,arg
    0.06
     уровня
    0.05
    Act Density 0.015%

    No Known Activations