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

    Neuronpedia

    INDEX
    Explanations

    example stop word: the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     straining
    0.45
     melts
    0.41
     galactose
    0.41
     packageName
    0.40
     mLast
    0.39
    }\|_{
    0.39
    蒼
    0.39
     ventilation
    0.39
     ventil
    0.39
    )=\{
    0.39
    POSITIVE LOGITS
    ]]
    0.61
    ]].
    0.59
    ']],
    0.51
     ]]
    0.50
    ']]
    0.49
    ]],
    0.44
    ordinated
    0.43
    ]];
    0.43
    ]]$
    0.42
    odos
    0.41
    Act Density 0.000%

    No Known Activations