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

    Neuronpedia

    INDEX
    Explanations

    "a" or "##"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deinen
    0.40
     deine
    0.37
     нен
    0.36
     שלך
    0.36
    agni
    0.35
    🔭
    0.35
     тво
    0.34
    OfInterest
    0.34
     لديك
    0.34
     விள
    0.34
    POSITIVE LOGITS
     SVP
    0.39
    ersham
    0.38
     paranoid
    0.37
    upaten
    0.37
    hauled
    0.37
     billet
    0.37
    ᖇ
    0.37
     Meso
    0.37
    éricas
    0.36
    ورية
    0.36
    Act Density 0.068%

    No Known Activations