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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     numbering
    -0.07
    勤
    -0.06
    لح
    -0.06
    leriyle
    -0.06
    ]));↵↵
    -0.06
     etk
    -0.06
    џЭ
    -0.06
    _tri
    -0.06
    ;l
    -0.06
    Declared
    -0.06
    POSITIVE LOGITS
     warfare
    0.07
     Italy
    0.06
    olución
    0.06
     PNG
    0.06
     Harold
    0.06
     behind
    0.06
    ولي
    0.06
    ンジ
    0.06
    nonnull
    0.06
     Gerry
    0.06
    Act Density 0.045%

    No Known Activations