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

    Neuronpedia

    INDEX
    Explanations

    Tiger

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     servlet
    -0.07
    -even
    -0.06
     Kel
    -0.06
     Clear
    -0.06
    isEqual
    -0.06
     ------------------------------------------------------------------------↵
    -0.06
     conjunto
    -0.06
    -suite
    -0.06
    दर
    -0.06
    Rib
    -0.06
    POSITIVE LOGITS
     distracted
    0.07
    カテゴリ
    0.06
    ?"↵↵↵↵
    0.06
     kırmızı
    0.06
     og
    0.06
    пи
    0.06
    jas
    0.06
    Ultra
    0.06
    ();↵↵↵↵
    0.06
     Santiago
    0.06
    Act Density 0.000%

    No Known Activations