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

    Neuronpedia

    INDEX
    Explanations

    specify locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ℡
    0.41
    ︾
    0.41
     mở
    0.40
     오픈
    0.40
     conversaciones
    0.39
     hablado
    0.39
     otvore
    0.39
     பேச்சு
    0.38
    聊
    0.38
    ائیں
    0.38
    POSITIVE LOGITS
     asking
    0.41
     Specify
    0.41
    問
    0.41
     Asking
    0.40
     Uganda
    0.40
     Brisbane
    0.39
     asks
    0.39
     specify
    0.39
     Nairobi
    0.39
     Canberra
    0.39
    Act Density 0.000%

    No Known Activations