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

    Neuronpedia

    INDEX
    Explanations

    in sync or in order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HttpSecurity
    0.71
    vislosti
    0.70
    खाली
    0.70
    ímenes
    0.70
     ماحول
    0.69
     környez
    0.67
    iterranean
    0.67
    addresses
    0.67
    టువంటి
    0.66
     emozioni
    0.65
    POSITIVE LOGITS
     sync
    0.95
     line
    0.92
     alignment
    0.87
     tune
    0.87
     whack
    0.84
     balance
    0.81
     contention
    0.80
     track
    0.79
     syn
    0.78
     view
    0.78
    Act Density 0.086%

    No Known Activations