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

    Neuronpedia

    INDEX
    Explanations

    licensing and inversion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    el
    0.48
    대
    0.45
    ال
    0.44
    academic
    0.43
    Cuál
    0.43
    eto
    0.42
    实现
    0.42
    𝚕
    0.42
    shift
    0.42
    ਇ
    0.42
    POSITIVE LOGITS
     nmea
    0.46
     ۾
    0.44
     tweak
    0.43
     fortfarande
    0.42
     telef
    0.41
    Phones
    0.41
     telephones
    0.40
     ponsel
    0.40
     tweaks
    0.40
    Reached
    0.40
    Act Density 0.024%

    No Known Activations