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

    Neuronpedia

    INDEX
    Explanations

    reflection and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oles
    1.11
     ένα
    1.06
    ens
    1.05
     étudier
    1.02
    ari
    1.00
    ä
    0.98
    ust
    0.97
    ik
    0.96
    rop
    0.94
    ug
    0.93
    POSITIVE LOGITS
    。
    1.16
    دي
    1.15
    G
    1.09
    D
    1.09
     reflect
    1.07
    تها
    1.07
     પ્રતિબિં
    1.05
    M
    1.03
    P
    1.02
    سي
    1.00
    Act Density 0.043%

    No Known Activations