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

    Neuronpedia

    INDEX
    Explanations

    brachycephaly, Infinity, medical report

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doesn
    0.55
     brainstorming
    0.49
     didn
    0.48
     plupart
    0.47
     bungee
    0.46
     Deli
    0.45
     dragged
    0.45
     brainstorm
    0.45
     néhány
    0.45
    ওয়ে
    0.44
    POSITIVE LOGITS
    证
    0.49
     판단
    0.49
    ну
    0.46
     veracity
    0.46
     credence
    0.45
     Ответ
    0.44
    д
    0.44
    су
    0.44
    正確
    0.44
    ériques
    0.43
    Act Density 0.000%

    No Known Activations