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

    Neuronpedia

    INDEX
    Explanations

    ids in URLs and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]];
    0.61
    ]]
    0.52
    ]],
    0.43
    ]].
    0.43
     eingel
    0.42
    Alfred
    0.41
    Alta
    0.41
    ]]:
    0.41
    ]]=
    0.40
    ünst
    0.39
    POSITIVE LOGITS
     nak
    0.45
    同比
    0.44
     upon
    0.43
     trên
    0.41
     (\$
    0.38
     rul
    0.37
    녈
    0.36
     Nc
    0.36
     idea
    0.36
     ly
    0.35
    Act Density 0.001%

    No Known Activations