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

    Neuronpedia

    INDEX
    Explanations

    names followed by associated terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਾ
    1.16
    ه
    1.09
    ↵
    1.04
    %
    1.01
    د
    1.00
    ల
    0.99
    h
    0.98
    _
    0.97
    ৫
    0.97
     or
    0.96
    POSITIVE LOGITS
    𝐨
    1.24
    تری
    1.10
    𝐢
    1.09
    تين
    1.08
    1
    1.06
    、
    1.05
     تقديم
    1.05
    𝐜
    1.05
     магнит
    1.03
    ت
    1.03
    Act Density 0.005%

    No Known Activations