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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ATTRIB
    -0.07
     týden
    -0.06
     П
    -0.06
     Ring
    -0.06
     адже
    -0.06
    Warn
    -0.06
     Волод
    -0.06
     Dương
    -0.06
    _DD
    -0.06
    673
    -0.06
    POSITIVE LOGITS
     initialize
    0.07
    raries
    0.07
     dří
    0.07
     refreshToken
    0.07
    credentials
    0.07
    isser
    0.07
    ;',↵
    0.07
     Unicorn
    0.06
    ;n
    0.06
    .Cor
    0.06
    Act Density 0.004%

    No Known Activations