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

    Neuronpedia

    INDEX
    Explanations

    adding or appending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     செயல்படுத்த
    0.65
    ösen
    0.63
     mantras
    0.62
     দূতাব
    0.62
     Ausgang
    0.62
     estimation
    0.61
     ternyata
    0.59
     गुज
    0.59
     seluruh
    0.59
    getenv
    0.59
    POSITIVE LOGITS
     adding
    2.71
     Add
    2.63
     Adding
    2.58
     add
    2.58
    Add
    2.56
    Adding
    2.50
    add
    2.48
     additions
    2.43
    添加
    2.38
    adding
    2.36
    Act Density 0.814%

    No Known Activations