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

    Neuronpedia

    INDEX
    Explanations

    объем

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     voluntarios
    0.54
    Во
    0.46
    woch
    0.46
    volunteer
    0.46
    во
    0.44
     vol
    0.43
     Вол
    0.43
     βο
    0.42
    Vol
    0.42
     volunteers
    0.42
    POSITIVE LOGITS
     obj
    1.62
     об
    1.45
    obj
    1.41
    Obj
    1.27
    體
    1.25
     Ob
    1.23
     OBJ
    1.23
     thể
    1.16
     Obj
    1.12
     体
    1.09
    Act Density 0.001%

    No Known Activations