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

    Neuronpedia

    INDEX
    Explanations

    client understands legal processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cosx
    0.50
    al
    0.50
    ney
    0.49
    و
    0.49
    oitte
    0.48
    @[
    0.47
    OfDeath
    0.47
    ofil
    0.47
     રાહ
    0.46
    of
    0.46
    POSITIVE LOGITS
     emphasize
    0.51
     SOD
    0.50
    ｳ
    0.47
     emphasise
    0.46
     ages
    0.45
     exports
    0.45
     characterize
    0.45
     identify
    0.45
     my
    0.44
     intel
    0.44
    Act Density 0.002%

    No Known Activations