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

    Neuronpedia

    INDEX
    Explanations

    disambiguation pages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]))
    -0.07
    免
    -0.07
    ectors
    -0.06
    ForgeryToken
    -0.06
    :");
↵
    -0.06
    ']):
    -0.06
    _PROXY
    -0.06
    _greater
    -0.06
    ];
↵
    -0.06
     ))
    -0.06
    POSITIVE LOGITS
    ossa
    0.06
     koup
    0.06
     Georges
    0.06
    charged
    0.06
    .Init
    0.06
    (user
    0.06
    .Storage
    0.06
     barr
    0.06
     assisting
    0.06
    vez
    0.06
    Act Density 0.003%

    No Known Activations