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

    Neuronpedia

    INDEX
    Explanations

    time references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quantité
    0.22
     nCmd
    0.21
    农
    0.20
    码
    0.19
     chăm
    0.19
    ﻞ
    0.19
    复杂
    0.18
    解释
    0.18
    负载
    0.18
     obfusc
    0.18
    POSITIVE LOGITS
     September
    0.42
     November
    0.42
    September
    0.40
     October
    0.40
     December
    0.39
     February
    0.37
    November
    0.37
     August
    0.36
     January
    0.36
     April
    0.36
    Act Density 0.110%

    No Known Activations