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

    Neuronpedia

    INDEX
    Explanations

    Thank you, we will contact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Junior
    -0.07
     junior
    -0.06
    _normalize
    -0.06
     predicting
    -0.06
    IRS
    -0.06
     �
    -0.06
    scale
    -0.06
     прой
    -0.06
    Junior
    -0.06
    unable
    -0.06
    POSITIVE LOGITS
     섬
    0.07
     Exiting
    0.07
    siyon
    0.06
    北京
    0.06
    _docs
    0.06
    เม
    0.06
    vro
    0.06
     parallels
    0.06
     یه
    0.06
    ا�
    0.06
    Act Density 0.001%

    No Known Activations