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

    Neuronpedia

    INDEX
    Explanations

    understanding concepts or language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ၊
    1.08
    không
    1.07
    ،
    1.02
    Е
    1.01
    to
    0.98
    ，“
    0.97
    、
    0.96
    nten
    0.93
    ，
    0.89
    nh
    0.88
    POSITIVE LOGITS
    ר
    2.00
    ת
    1.59
    :
    1.36
    י
    1.27
    ה
    1.20
    /
    1.17
    ות
    1.12
    น
    1.09
     K
    1.05
     the
    1.04
    Act Density 0.236%

    No Known Activations