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

    Neuronpedia

    INDEX
    Explanations

    Configuration files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     веч
    -0.08
     الجمه
    -0.07
    コミュニ
    -0.07
    �
    -0.07
    receipt
    -0.07
     völl
    -0.07
    universal
    -0.07
     atmospheric
    -0.07
    谊
    -0.07
    -vis
    -0.07
    POSITIVE LOGITS
    つ
    0.07
    Young
    0.07
    责任制
    0.06
    INO
    0.06
    .Group
    0.06
     youngster
    0.06
    .toolStripButton
    0.06
    "&
    0.06
     Administrator
    0.06
    مر
    0.06
    Act Density 0.004%

    No Known Activations