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

    Neuronpedia

    INDEX
    Explanations

    Google Search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اهای
    0.70
    opolar
    0.70
     politič
    0.70
     držav
    0.70
     Phaser
    0.69
     রাষ্ট্রীয়
    0.69
    ísticos
    0.68
     Pho
    0.67
    褓
    0.67
    ደጋ
    0.66
    POSITIVE LOGITS
    arette
    0.67
    outing
    0.65
     लिहिले
    0.64
     σύ
    0.64
     paint
    0.63
     App
    0.60
     Return
    0.60
     br
    0.59
    ্ত
    0.59
     Application
    0.58
    Act Density 0.014%

    No Known Activations