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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    們
    -0.08
    ---------↵↵
    -0.08
     gị
    -0.07
    아이
    -0.07
    ейн
    -0.07
    --------------↵↵
    -0.07
     JPanel
    -0.07
     ihren
    -0.07
    entscheidung
    -0.07
     শত
    -0.07
    POSITIVE LOGITS
     cri
    0.08
     coverage
    0.08
     uptime
    0.08
     nonsense
    0.08
     Wisdom
    0.08
     Vertrauen
    0.07
    连续
    0.07
     Dien
    0.07
     �
    0.07
     sugar
    0.07
    Act Density 0.034%

    No Known Activations