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

    Neuronpedia

    INDEX
    Explanations

    self-attention explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Enabled
    0.49
    㙅
    0.48
    畽
    0.48
     Kaltura
    0.47
    雅黑
    0.47
     পুরাতন
    0.46
    Ⲃ
    0.46
    OAc
    0.46
    Enhanced
    0.46
    焲
    0.46
    POSITIVE LOGITS
    מש
    0.50
     shoulder
    0.47
    sponge
    0.46
     wearer
    0.46
    அ
    0.46
     rodz
    0.45
     sponge
    0.45
     ghostly
    0.45
     suerte
    0.45
     curvy
    0.45
    Act Density 0.003%

    No Known Activations