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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Factories
    -0.06
    /unit
    -0.06
     congr
    -0.06
    _steps
    -0.06
    ccording
    -0.06
    ello
    -0.06
    .types
    -0.06
    roken
    -0.06
     Rolls
    -0.06
     Αν
    -0.06
    POSITIVE LOGITS
     группы
    0.07
     _______,
    0.06
     ayud
    0.06
     Ay
    0.06
     grit
    0.06
    啊
    0.06
     Sig
    0.06
    izzy
    0.06
     Ian
    0.06
    李
    0.06
    Act Density 0.000%

    No Known Activations