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

    Neuronpedia

    INDEX
    Explanations

    terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
    ποι
    -0.06
    خاب
    -0.06
    ancybox
    -0.06
     alcuni
    -0.06
    컬
    -0.06
    (cd
    -0.06
    "]
↵
    -0.06
    ีโอ
    -0.06
    ディース
    -0.06
    POSITIVE LOGITS
    etime
    0.07
    Purpose
    0.06
     promptly
    0.06
     affirm
    0.06
    %M
    0.06
     Confirm
    0.06
     Marble
    0.06
     mute
    0.06
     مار
    0.06
     autor
    0.06
    Act Density 0.003%

    No Known Activations