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

    Neuronpedia

    INDEX
    Explanations

    typo corrections and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $,
    0.76
     ،
    0.67
    থেষ্ট
    0.64
     ၊
    0.64
    ᅭ
    0.63
     तभी
    0.61
    inding
    0.60
     దాని
    0.59
     Burgundy
    0.59
    льній
    0.59
    POSITIVE LOGITS
    га
    0.96
    R
    0.96
    س
    0.96
    S
    0.96
    ко
    0.95
    3
    0.93
    P
    0.88
    o
    0.87
    ק
    0.87
    D
    0.83
    Act Density 0.000%

    No Known Activations