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

    Neuronpedia

    INDEX
    Explanations

    ellipses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     azt
    -0.06
     Donne
    -0.06
    <Token
    -0.06
     Loài
    -0.06
     faults
    -0.06
    〃
    -0.06
    Proceed
    -0.06
    rored
    -0.06
     quot
    -0.06
     мног
    -0.06
    POSITIVE LOGITS
    **)
    0.07
    ubectl
    0.07
    _present
    0.07
    지는
    0.06
    .magnitude
    0.06
     방송
    0.06
    ologne
    0.06
    \Admin
    0.06
    ++)
↵
    0.06
     Mrs
    0.06
    Act Density 0.003%

    No Known Activations