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

    Neuronpedia

    INDEX
    Explanations

    open source licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alarms
    0.70
     sabot
    0.65
     nacht
    0.62
     romans
    0.61
     når
    0.61
     parlé
    0.60
     kada
    0.59
     spasms
    0.59
     bipart
    0.59
     waveforms
    0.58
    POSITIVE LOGITS
    ЕР
    0.58
    ۰
    0.57
    ribution
    0.57
     Wikimedia
    0.55
    <0x80>
    0.53
    ин
    0.53
    Ин
    0.53
    pose
    0.52
    ando
    0.51
    ИН
    0.50
    Act Density 0.051%

    No Known Activations