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

    Neuronpedia

    INDEX
    Explanations

    в или a difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     |
    0.94
     ،
    0.92
     ,
    0.90
    ،
    0.89
     -
    0.88
    ↵
    0.87
    :
    0.86
    ",
    0.85
     [
    0.84
    .
    0.84
    POSITIVE LOGITS
    ꩡ
    0.90
     absurdity
    0.88
     isso
    0.88
    ставля
    0.87
    ິດ
    0.87
    owały
    0.87
     таком
    0.84
     manglid
    0.84
    𝚞
    0.84
    нят
    0.84
    Act Density 0.010%

    No Known Activations