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

    Neuronpedia

    INDEX
    Explanations

    outcomes and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     এবং
    2.78
     और
    2.75
     आणि
    2.73
     and
    2.70
    และ
    2.60
     અને
    2.59
     и
    2.54
     và
    2.52
    और
    2.49
    和
    2.48
    POSITIVE LOGITS
    <unused42>
    0.99
     accordingly
    0.87
    <unused49>
    0.85
    ?,?,
    0.79
     against
    0.78
     rather
    0.76
     wherever
    0.76
     Rather
    0.76
     gegenüber
    0.76
     through
    0.75
    Act Density 0.255%

    No Known Activations