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

    Neuronpedia

    INDEX
    Explanations

    they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stone
    -0.08
    ]==
    -0.07
     homeowners
    -0.06
     unary
    -0.06
    xico
    -0.06
     peripherals
    -0.06
     sorry
    -0.06
     alternative
    -0.06
     учрежд
    -0.06
    \Application
    -0.06
    POSITIVE LOGITS
    ۲۶
    0.08
    —it
    0.08
     it
    0.08
     they
    0.08
    —they
    0.07
     cường
    0.07
    It
    0.07
    (indent
    0.07
     они
    0.07
    “It
    0.06
    Act Density 0.041%

    No Known Activations