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

    Neuronpedia

    INDEX
    Explanations

    linked accounts and dedicated service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ->
    0.48
     ("
    0.46
    !!!!!!!!
    0.45
    લિક
    0.44
     করিতেছে
    0.43
    ="..\
    0.42
    !!!!!!!!!!!!!!!!
    0.42
    尅
    0.42
    ၏
    0.41
     उसको
    0.41
    POSITIVE LOGITS
    ,”
    0.61
     ہماری
    0.58
    ),”
    0.57
     naszych
    0.52
    ,’’
    0.51
     meie
    0.50
     nostru
    0.50
     sabemos
    0.49
    ।”
    0.49
    ,\"
    0.49
    Act Density 0.025%

    No Known Activations