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

    Neuronpedia

    INDEX
    Explanations

    the followed by introducing words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ü
    1.55
    ს
    1.51
    কে
    1.45
    р
    1.43
    Г
    1.41
    А
    1.39
    7
    1.37
     rupam
    1.36
     seguida
    1.35
    6
    1.33
    POSITIVE LOGITS
    ophylline
    2.11
    mselves
    2.02
    യും
    1.40
    atrical
    1.35
    <bos>
    1.29
     same
    1.27
     ensuing
    1.27
    od
    1.25
     '>'
    1.23
     proverbial
    1.22
    Act Density 1.558%

    No Known Activations