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

    Neuronpedia

    INDEX
    Explanations

    `Replace` after `//` or `.`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nameSort
    0.77
    ায়ত্ত
    0.74
    AxisSize
    0.73
     malu
    0.70
     natoque
    0.66
    itektur
    0.65
     ዓይነ
    0.64
     tendencias
    0.64
    ృష్టి
    0.64
     dormir
    0.64
    POSITIVE LOGITS
     replacement
    5.44
     replace
    5.43
     replacing
    5.17
     Replace
    5.09
    Replace
    5.06
     replaced
    5.01
     Replacement
    5.01
     replacements
    4.98
    replace
    4.97
     replaces
    4.96
    Act Density 0.799%

    No Known Activations