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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liability
    -0.07
     respondent
    -0.07
    /pl
    -0.06
    _obs
    -0.06
    hide
    -0.06
     tension
    -0.06
    ams
    -0.06
    >y
    -0.06
     Unknown
    -0.06
     merchandise
    -0.06
    POSITIVE LOGITS
    要求
    0.07
     �
    0.07
     накоп
    0.07
    收录
    0.07
     öne
    0.06
    ')):↵
    0.06
     نظام
    0.06
    ]);
    0.06
    ])),
    0.06
     cinsel
    0.06
    Act Density 0.049%

    No Known Activations