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

    Neuronpedia

    INDEX
    Explanations

    center center

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lack
    0.38
     alguns
    0.37
    lessis
    0.37
    失去
    0.36
    osed
    0.35
    nemidophorus
    0.35
     lizenz
    0.34
     loosing
    0.34
     losing
    0.34
     FDI
    0.34
    POSITIVE LOGITS
     dom
    0.43
     പരി
    0.38
    精
    0.38
    setPassword
    0.38
    creatic
    0.37
     精
    0.37
    shel
    0.37
    collections
    0.37
    mechan
    0.37
    greet
    0.37
    Act Density 0.000%

    No Known Activations