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

    Neuronpedia

    INDEX
    Explanations

    when you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    0.51
    ry
    0.50
    y
    0.46
    backs
    0.46
    ca
    0.45
    v
    0.44
    R
    0.44
    奻
    0.43
     नीचे
    0.43
    of
    0.43
    POSITIVE LOGITS
     legisl
    0.48
    缥
    0.45
    শিরোনাম
    0.45
     Legisl
    0.44
     fusion
    0.44
     appliances
    0.44
     conseguir
    0.44
     retribution
    0.43
     Fusion
    0.43
     tình
    0.43
    Act Density 0.000%

    No Known Activations