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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    3.68
    лно
    3.59
    ل
    3.55
    l
    3.52
    ০
    3.33
    en
    3.27
    ená
    3.09
    лни
    3.08
    ר
    3.04
    лна
    2.97
    POSITIVE LOGITS
    NOWLEDG
    2.65
    !\!\
    2.42
    ainte
    2.35
     armada
    2.33
     κι
    2.29
    ༌
    2.28
    髏
    2.25
    ','"+
    2.24
    𝔰
    2.21
    𝐫
    2.21
    Act Density 0.043%

    No Known Activations