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

    Neuronpedia

    INDEX
    Explanations

    Indian names and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bao
    1.03
     dữ
    1.01
     phá
    0.97
     tham
    0.96
     відбувається
    0.91
     kullan
    0.91
     진행
    0.90
     poate
    0.89
     bude
    0.89
     fazer
    0.89
    POSITIVE LOGITS
     की
    0.96
    ०
    0.85
     के
    0.85
     उन्हें
    0.85
    чно
    0.85
    ा
    0.83
    ं
    0.82
     वे
    0.80
     से
    0.80
    жной
    0.80
    Act Density 0.005%

    No Known Activations