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

    Neuronpedia

    INDEX
    Explanations

    building details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bigli
    0.50
    ವರೆ
    0.48
    брав
    0.47
    garia
    0.45
    引き続き
    0.45
    Political
    0.44
    ृती
    0.43
    Trashed
    0.42
    abhut
    0.42
     CHAR
    0.42
    POSITIVE LOGITS
     appraisals
    0.49
     Begriffe
    0.48
     irrational
    0.46
     Ideen
    0.45
     Folge
    0.44
    rums
    0.43
     Dinge
    0.43
     kaleidos
    0.43
     innovations
    0.42
     Ihr
    0.42
    Act Density 0.008%

    No Known Activations