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

    Neuronpedia

    INDEX
    Explanations

    different purposes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ی
    1.62
    7
    1.60
    PER
    1.58
    6
    1.56
    9
    1.54
    2
    1.52
    1
    1.52
     prona
    1.48
    5
    1.48
    0
    1.46
    POSITIVE LOGITS
     purposes
    2.30
     starters
    1.83
    asmuch
    1.73
     sake
    1.66
    来说
    1.64
     awhile
    1.59
    giveness
    1.48
     Purposes
    1.47
     Damages
    1.43
     fragen
    1.42
    Act Density 0.437%

    No Known Activations