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
     Est
    -0.07
    Dream
    -0.06
    cord
    -0.06
    ;text
    -0.06
    WASHINGTON
    -0.06
     paced
    -0.06
    해서
    -0.06
    기로
    -0.06
     थ
    -0.06
    ubby
    -0.06
    POSITIVE LOGITS
    .datasource
    0.08
     Mini
    0.06
    ->↵
    0.06
     peasants
    0.06
    -feira
    0.06
    ]:↵
    0.06
    ิตภ
    0.06
    olithic
    0.06
     +#+#+#+
    0.06
    _RSA
    0.06
    Act Density 0.351%

    No Known Activations