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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ást
    0.66
     Quanto
    0.65
    ppies
    0.62
     Sond
    0.61
    ueill
    0.61
     quanto
    0.60
     Vent
    0.60
    Quanto
    0.59
    सुन
    0.59
    quanto
    0.59
    POSITIVE LOGITS
     on
    2.90
     trên
    2.07
     على
    2.06
    บน
    1.99
     On
    1.98
    On
    1.93
     på
    1.88
     pada
    1.87
    于
    1.85
     บน
    1.82
    Act Density 0.282%

    No Known Activations