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

    Neuronpedia

    INDEX
    Explanations

    math calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mnie
    -0.07
    gx
    -0.07
     Kirk
    -0.07
     Benn
    -0.06
     founded
    -0.06
    нуть
    -0.06
    ricks
    -0.06
    theta
    -0.06
     altına
    -0.06
    erto
    -0.06
    POSITIVE LOGITS
     transport
    0.07
    :not
    0.06
    .getResources
    0.06
     REFER
    0.06
     bear
    0.06
     Concrete
    0.06
    _transport
    0.06
     символ
    0.06
    /code
    0.06
    emp
    0.06
    Act Density 0.034%

    No Known Activations