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

    Neuronpedia

    INDEX
    Explanations

    quality and descriptive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     biofilms
    0.44
     ایمان
    0.41
     συνεχ
    0.41
     opioids
    0.41
     mengakses
    0.38
     subTest
    0.37
     lagoons
    0.36
     biofilm
    0.36
     œuvres
    0.36
    ノン
    0.35
    POSITIVE LOGITS
     Can
    0.43
    al
    0.42
    ing
    0.41
    un
    0.41
    fine
    0.40
    can
    0.40
    man
    0.39
    va
    0.38
    class
    0.38
    reply
    0.38
    Act Density 0.000%

    No Known Activations