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

    Neuronpedia

    INDEX
    Explanations

    numerical ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]]).
    0.37
    osan
    0.36
     spectrophot
    0.35
     בשנת
    0.35
     nearly
    0.34
    았던
    0.34
    வுக்கு
    0.34
    كة
    0.33
     halfway
    0.32
    स्ताना
    0.32
    POSITIVE LOGITS
     between
    0.98
     mellom
    0.94
     zwischen
    0.93
    between
    0.93
     tussen
    0.93
     ranging
    0.92
     mellan
    0.91
     mellem
    0.90
     између
    0.89
     Between
    0.87
    Act Density 0.137%

    No Known Activations