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

    Neuronpedia

    INDEX
    Explanations

    #4CAF50

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    仯
    0.39
     TextEditing
    0.38
    價值
    0.38
    achery
    0.37
    閨
    0.37
     čty
    0.37
     dwa
    0.37
    ที่เป็น
    0.36
    獲
    0.36
     भर्त
    0.35
    POSITIVE LOGITS
    7
    0.50
    6
    0.39
    ೭
    0.37
    8
    0.36
     confronted
    0.35
     unstable
    0.34
    etheus
    0.34
     primes
    0.34
     mindestens
    0.34
    不定
    0.34
    Act Density 0.002%

    No Known Activations