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

    Neuronpedia

    INDEX
    Explanations

    less than or greater than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Policía
    0.43
     polícia
    0.40
     police
    0.39
    ías
    0.38
     División
    0.38
     pedi
    0.37
     Çalış
    0.37
     qilish
    0.37
     않은
    0.37
     उसमे
    0.37
    POSITIVE LOGITS
    ?
    0.33
    $$\
    0.33
    <&
    0.32
    Updates
    0.31
    illum
    0.31
    sh
    0.30
    cdot
    0.30
    shim
    0.30
    ちなみに
    0.30
    spannung
    0.30
    Act Density 0.000%

    No Known Activations