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

    Neuronpedia

    INDEX
    Explanations

    century, chart, frames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ureka
    0.53
     Publ
    0.53
    偎
    0.53
    ektir
    0.48
    ed
    0.47
    ímica
    0.46
    que
    0.46
    Indexer
    0.46
    语
    0.46
    Петер
    0.45
    POSITIVE LOGITS
     shrub
    0.49
     reconstructions
    0.45
    ﮢ
    0.44
     plantations
    0.43
     OWL
    0.42
     harsher
    0.42
     herringbone
    0.42
    種の
    0.42
    স
    0.42
    """
    0.42
    Act Density 0.000%

    No Known Activations