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

    Neuronpedia

    INDEX
    Explanations

    name attribute assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ఉన్న
    0.71
    .​
    0.69
     verwendeten
    0.67
    的书
    0.66
     Russland
    0.66
     பேசு
    0.65
     Vorteil
    0.64
     Sprach
    0.63
     geldig
    0.63
     tätig
    0.63
    POSITIVE LOGITS
     is
    0.95
     the
    0.86
    k
    0.85
    l
    0.79
    ל
    0.72
     conjecture
    0.66
    '
    0.66
    ल
    0.66
     has
    0.64
    iles
    0.62
    Act Density 0.001%

    No Known Activations