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

    Neuronpedia

    INDEX
    Explanations

    can provide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    মেল
    0.38
    ехали
    0.38
    нија
    0.37
    এর
    0.37
    NELL
    0.37
    șit
    0.36
     Became
    0.36
     BLUENRG
    0.35
    選手の
    0.35
     Saif
    0.35
    POSITIVE LOGITS
     cá
    0.38
    Gestion
    0.38
    -"+
    0.37
    łod
    0.37
     exuber
    0.37
    分辨
    0.37
     كيفية
    0.36
     gestion
    0.36
    Fine
    0.35
     supone
    0.35
    Act Density 0.000%

    No Known Activations