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

    Neuronpedia

    INDEX
    Explanations

    warming drives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    formula
    0.43
    வதன்
    0.42
     формула
    0.40
    ηση
    0.40
    สู
    0.40
    Apex
    0.39
     सुविधा
    0.38
    computation
    0.38
     formula
    0.38
     дозво
    0.38
    POSITIVE LOGITS
     then
    0.59
     expressed
    0.47
    then
    0.46
     então
    0.46
     سپس
    0.46
     sitten
    0.46
     alors
    0.43
     enters
    0.43
    Then
    0.42
     creates
    0.42
    Act Density 0.000%

    No Known Activations