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

    Neuronpedia

    INDEX
    Explanations

    descriptive lists and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dali
    0.49
     Hogg
    0.48
    韜
    0.47
     wholeheartedly
    0.47
     বিদ্য
    0.47
     стрелец
    0.47
     Hoffnung
    0.45
     Hurd
    0.45
     เอก
    0.45
     本当
    0.44
    POSITIVE LOGITS
    can
    0.49
    ído
    0.47
    amento
    0.47
    hme
    0.47
    owe
    0.47
    '
    0.46
    с
    0.44
    ite
    0.44
    uz
    0.44
    closed
    0.44
    Act Density 3.000%

    No Known Activations