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

    Neuronpedia

    INDEX
    Explanations

    legal filings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     collusion
    -0.06
    LayoutInflater
    -0.06
     Forest
    -0.06
    ать
    -0.06
    ップ
    -0.06
     Master
    -0.06
     Factor
    -0.06
    樓
    -0.06
    ระ
    -0.06
     fuse
    -0.06
    POSITIVE LOGITS
    _VM
    0.07
    Bạn
    0.06
     quarterbacks
    0.06
    "]]↵
    0.06
    े-
    0.06
     [{↵
    0.06
    ")]
    0.06
     날
    0.06
     familial
    0.06
     jedno
    0.06
    Act Density 0.012%

    No Known Activations