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

    Neuronpedia

    INDEX
    Explanations

    Foreign word stems and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite

    word completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    1.48
    ia
    1.48
    am
    1.35
    ik
    1.32
    ab
    1.24
    ap
    1.18
     can
    1.14
    um
    1.11
    на
    1.09
    c
    1.09
    POSITIVE LOGITS
    2
    1.27
    4
    1.27
    8
    1.26
    5
    1.22
    9
    1.17
    ς
    1.09
    ਆਂ
    1.05
    7
    1.02
    ের
    1.02
    '
    1.00
    Act Density 0.089%

    No Known Activations