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

    Neuronpedia

    INDEX
    Explanations

    former + title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Currents
    1.99
    近く
    1.88
     puluh
    1.81
     poč
    1.75
     lưới
    1.70
     actionPerformed
    1.68
     closer
    1.66
     mucus
    1.59
    Ꮡ
    1.58
     attuned
    1.58
    POSITIVE LOGITS
     glories
    2.60
    ád
    1.96
     glory
    1.95
    past
    1.89
     cruciate
    1.89
    𝚝
    1.86
    persist
    1.86
     doğr
    1.86
    ți
    1.82
    𝚌
    1.81
    Act Density 0.006%

    No Known Activations