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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alors
    0.38
    有很多
    0.37
     encore
    0.37
     경우에는
    0.36
     VLC
    0.36
     Siamo
    0.36
    allen
    0.35
     oncoming
    0.35
     congratulations
    0.35
     allora
    0.34
    POSITIVE LOGITS
    ס
    0.42
    ‚
    0.40
    ద్
    0.40
     كذلك
    0.39
    ופ
    0.38
    დას
    0.37
     குளிர்
    0.37
     잠
    0.37
     עד
    0.37
     글
    0.37
    Act Density 0.012%

    No Known Activations