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

    Neuronpedia

    INDEX
    Explanations

    closing parentheses followed by code or identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ח
    0.58
    ，
    0.54
    。(
    0.53
    াস
    0.48
     другие
    0.48
     інші
    0.48
    GTEST
    0.47
    lis
    0.46
    ড়
    0.46
    (!
    0.46
    POSITIVE LOGITS
    لي
    0.69
    دي
    0.58
    ires
    0.56
     Jed
    0.55
    ى
    0.52
     Krzy
    0.51
    ви
    0.50
    ၃
    0.50
     Pigs
    0.49
     Jee
    0.49
    Act Density 0.127%

    No Known Activations