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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GetData
    -0.07
     الصحفي
    -0.06
    기에
    -0.06
    needs
    -0.06
     quote
    -0.06
    _link
    -0.06
     excellence
    -0.06
    Guest
    -0.06
    Now
    -0.06
    (QL
    -0.06
    POSITIVE LOGITS
    쌰
    0.07
    (str
    0.07
    횰
    0.06
    LIST
    0.06
     Deer
    0.06
    읜
    0.06
     Emb
    0.06
    pr
    0.06
    仟
    0.06
    }}],↵
    0.06
    Act Density 0.014%

    No Known Activations