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

    Neuronpedia

    INDEX
    Explanations

    honest and realistic agreements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     co
    0.36
     me
    0.35
     Co
    0.34
     Yet
    0.34
     Lauren
    0.34
     yet
    0.34
     Bills
    0.34
     Publish
    0.33
     ഞങ്ങൾ
    0.33
     demands
    0.33
    POSITIVE LOGITS
    gaussian
    0.37
    Backed
    0.37
     Engineered
    0.36
    inales
    0.36
    Ⴖ
    0.36
    "{@
    0.36
     جانتے
    0.35
    engineered
    0.34
    Лі
    0.34
     engineered
    0.34
    Act Density 0.009%

    No Known Activations