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
    显
    -0.08
    _FORCE
    -0.08
    ற்று
    -0.08
     saddle
    -0.08
    -force
    -0.08
    毕业
    -0.07
    orton
    -0.07
     போது
    -0.07
    _force
    -0.07
    टना
    -0.07
    POSITIVE LOGITS
     Generated
    0.08
     """↵↵
    0.08
     '''↵↵
    0.08
     Json
    0.07
    '''↵↵
    0.07
     Explained
    0.07
     PLEASE
    0.07
    ayey
    0.07
     Contains
    0.07
    індегі
    0.07
    Act Density 0.001%

    No Known Activations