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

    Neuronpedia

    INDEX
    Explanations

    health risks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ]);↵
    -0.08
    展
    -0.07
     })),↵
    -0.07
    卷
    -0.07
    ][$
    -0.07
    不远
    -0.07
     dbc
    -0.07
     hết
    -0.06
    (dist
    -0.06
     assisted
    -0.06
    POSITIVE LOGITS
     consolidate
    0.08
    变换
    0.07
     Memo
    0.06
    .Named
    0.06
     Actual
    0.06
    앤
    0.06
     brewers
    0.06
    Lock
    0.06
    iffies
    0.06
    _LCD
    0.06
    Act Density 0.033%

    No Known Activations