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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ],↵↵
    -0.08
     DAYS
    -0.07
     Graphics
    -0.07
     ),↵
    -0.07
    onta
    -0.07
    ubat
    -0.07
    _SUBJECT
    -0.07
    形
    -0.06
     agreement
    -0.06
    ]'↵
    -0.06
    POSITIVE LOGITS
     Administr
    0.06
     sammen
    0.06
    ۱۷
    0.06
    �
    0.06
    _expect
    0.05
    _dual
    0.05
    trigger
    0.05
    ыми
    0.05
     wij
    0.05
     opravdu
    0.05
    Act Density 0.032%

    No Known Activations