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

    Neuronpedia

    INDEX
    Explanations

    market and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eliers
    0.54
    StillWater
    0.52
    ister
    0.52
    llium
    0.52
    ΗΣ
    0.52
    ्ज
    0.51
    fler
    0.50
     διαδικ
    0.49
    ucchini
    0.49
    lerle
    0.49
    POSITIVE LOGITS
    #
    0.54
     canonical
    0.54
     danni
    0.53
     registered
    0.51
     funzionalità
    0.51
     النوم
    0.50
    0.50
    、
    0.50
     metadata
    0.50
    န့်
    0.49
    Act Density 0.000%

    No Known Activations