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

    Neuronpedia

    INDEX
    Explanations

    citation style

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olin
    0.42
     Steph
    0.39
    streak
    0.39
     bis
    0.38
    max
    0.37
     strand
    0.37
    startswith
    0.37
     Strand
    0.37
     longevity
    0.37
     streak
    0.37
    POSITIVE LOGITS
     অনুপ্র
    0.45
     Mice
    0.42
     বঞ্চিত
    0.42
     Taxonomic
    0.40
     illiterate
    0.39
    㮆
    0.38
    龧
    0.38
    光学
    0.37
    දර
    0.37
     அன்பு
    0.36
    Act Density 0.001%

    No Known Activations