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

    Neuronpedia

    INDEX
    Explanations

    questions and topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Whilst
    0.61
     Entretanto
    0.58
     oftentimes
    0.53
     Whilst
    0.52
    Alright
    0.46
    কোনও
    0.45
    设定
    0.44
    亟
    0.44
     takePhotoButton
    0.43
    ﹟
    0.42
    POSITIVE LOGITS
    :-
    0.71
     few
    0.65
     same
    0.64
     :-
    0.61
     needy
    0.61
     upto
    0.57
     saper
    0.56
    few
    0.55
     क्यो
    0.55
     peoples
    0.55
    Act Density 0.062%

    No Known Activations