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

    Neuronpedia

    INDEX
    Explanations

    change, add, clarify, write

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     guter
    0.41
     slowed
    0.39
     impacted
    0.39
     рівня
    0.39
     levels
    0.39
    ⬤
    0.39
     golfers
    0.38
     THREE
    0.38
     Three
    0.38
     staunch
    0.37
    POSITIVE LOGITS
    жности
    0.47
    ToAdd
    0.46
     تغییر
    0.45
    ToWrite
    0.44
    toadd
    0.44
    변경
    0.43
     elucidation
    0.43
     clarification
    0.42
     Änderung
    0.42
    ཎ
    0.42
    Act Density 0.001%

    No Known Activations