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

    Neuronpedia

    INDEX
    Explanations

    tropes and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unile
    0.47
    ombok
    0.43
    waar
    0.43
    obby
    0.42
    ższ
    0.41
    jskiej
    0.40
    隐含规则
    0.40
    軲
    0.39
    जिद
    0.39
    雳
    0.38
    POSITIVE LOGITS
    е
    1.58
    e
    1.54
    es
    1.52
    elike
    1.34
    eless
    1.32
    E
    1.30
    ｅ
    1.28
    ე
    1.25
    𝗲
    1.23
    𝒆
    1.18
    Act Density 0.110%

    No Known Activations