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

    Neuronpedia

    INDEX
    Explanations

    in a way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     modalità
    0.47
     условиях
    0.45
     méthodes
    0.45
    DHL
    0.44
     formats
    0.44
    ান্স
    0.43
     угол
    0.43
     situations
    0.42
     backgrounds
    0.42
    Gift
    0.41
    POSITIVE LOGITS
     way
    0.57
     Way
    0.50
     WAY
    0.46
    Way
    0.44
    way
    0.43
    WAY
    0.38
    nament
    0.37
     вещи
    0.37
     respecto
    0.35
    etva
    0.35
    Act Density 0.022%

    No Known Activations