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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wrap
    -0.06
    andon
    -0.06
    Í
    -0.06
    })();↵
    -0.06
    usan
    -0.06
     △
    -0.06
     Simpson
    -0.06
    گرد
    -0.05
     jet
    -0.05
    ंजन
    -0.05
    POSITIVE LOGITS
     issu
    0.08
    prü
    0.08
     weitere
    0.07
     erad
    0.07
     других
    0.07
    _UT
    0.07
    нав
    0.06
     savaş
    0.06
    [right
    0.06
    hapus
    0.06
    Act Density 0.023%

    No Known Activations