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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MAR
    -0.08
     kavram
    -0.07
     revelation
    -0.07
     河
    -0.07
    存在
    -0.07
    earch
    -0.07
    window
    -0.06
    銀
    -0.06
     yanı
    -0.06
    nictvím
    -0.06
    POSITIVE LOGITS
     kalk
    0.08
    #elif
    0.07
    _MP
    0.06
     Originally
    0.06
    Genres
    0.06
     回
    0.06
     kontro
    0.06
     ushort
    0.06
     beam
    0.06
     QMessageBox
    0.06
    Act Density 0.036%

    No Known Activations