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

    Neuronpedia

    INDEX
    Explanations

    bold markers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     사람
    0.67
     यही
    0.52
    が
    0.50
    가
    0.50
    A
    0.49
    :
    0.47
    S
    0.46
    D
    0.46
    は
    0.46
    N
    0.45
    POSITIVE LOGITS
    ↵↵
    0.93
    ↵
    0.74
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.69
     ⠀
    0.66
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.64
    ↵↵↵↵↵
    0.64
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.64
     、,
    0.64
    ↵↵↵↵
    0.63
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.63
    Act Density 0.201%

    No Known Activations