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

    Neuronpedia

    INDEX
    Explanations

    range and image

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нали
    0.57
     одним
    0.54
    inplace
    0.51
    тельностью
    0.51
     strum
    0.51
    ویزی
    0.51
    kosť
    0.51
    ренности
    0.51
    
    0.50
    Роз
    0.50
    POSITIVE LOGITS
     can
    0.64
    4
    0.64
    8
    0.63
     Outlet
    0.61
    5
    0.61
    2
    0.58
     to
    0.57
     went
    0.57
    }{\
    0.57
    s
    0.57
    Act Density 0.002%

    No Known Activations