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

    Neuronpedia

    INDEX
    Explanations

    manner of action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appunto
    0.33
    вы
    0.28
     Pandit
    0.28
     だっ
    0.27
     বিনাম
    0.26
     które
    0.26
     অশ
    0.26
    ходе
    0.26
    嬅
    0.26
     vand
    0.26
    POSITIVE LOGITS
    पणे
    0.43
    lessly
    0.41
    ely
    0.41
    ently
    0.38
     into
    0.37
    mente
    0.37
    osamente
    0.36
    ishly
    0.36
    aneously
    0.36
     enough
    0.36
    Act Density 0.078%

    No Known Activations