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

    Neuronpedia

    INDEX
    Explanations

    non-English characters or code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    त
    0.51
    Provision
    0.48
    ٔ
    0.46
    Provides
    0.45
    أ
    0.45
    WB
    0.44
    तलब
    0.44
    이자
    0.44
     रिपोर्ट्स
    0.44
    해
    0.43
    POSITIVE LOGITS
     plas
    0.52
    '";
    0.50
    ]);
    0.49
     அனுப
    0.47
     এটা
    0.47
     findPlayer
    0.47
     گستر
    0.46
     progressivement
    0.45
     dhammo
    0.45
     δια
    0.45
    Act Density 0.111%

    No Known Activations