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

    Neuronpedia

    INDEX
    Explanations

    XML namespace or template

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Њ
    1.16
     kez
    1.11
    的想法
    1.08
    heus
    1.05
     potency
    1.03
    店舗
    1.00
     consultation
    0.97
    ون
    0.97
    .,
    0.96
     pageWidth
    0.96
    POSITIVE LOGITS
    1.40
    ❒
    1.34
    llä
    1.33
    𝐭
    1.30
    ♦
    1.28
    ❐
    1.28
    芦
    1.24
    𝘨
    1.22
    ن
    1.21
    1.19
    Act Density 0.019%

    No Known Activations