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

    Neuronpedia

    INDEX
    Explanations

    subjects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     height
    -0.07
     payments
    -0.07
     jc
    -0.06
    ederation
    -0.06
    plugin
    -0.06
    ATTRIBUTE
    -0.06
     receipts
    -0.06
    unny
    -0.06
    　　
    -0.06
    _ERROR
    -0.06
    POSITIVE LOGITS
    _l
    0.06
    umlu
    0.06
    *u
    0.06
     deix
    0.06
    kových
    0.06
    怎么
    0.06
    666
    0.06
     příliš
    0.06
     automat
    0.06
     semua
    0.06
    Act Density 0.033%

    No Known Activations