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

    Neuronpedia

    INDEX
    Explanations

    systematic examination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ibas
    0.52
     આપે
    0.43
    ܥ
    0.41
    放出
    0.40
    Ꭹ
    0.39
    viii
    0.39
     নেতাকর্ম
    0.38
    ainer
    0.37
     creme
    0.37
     Creme
    0.37
    POSITIVE LOGITS
     ફર
    0.44
     interi
    0.40
     extranjeros
    0.39
     Porque
    0.39
    挑战
    0.38
     Nurse
    0.37
     Because
    0.37
     Primitive
    0.36
    Prevention
    0.36
     entirely
    0.36
    Act Density 0.000%

    No Known Activations