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

    Neuronpedia

    INDEX
    Explanations

    remembering things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     РФ
    0.61
    楽曲
    0.56
    撸
    0.53
    翀
    0.52
     ракет
    0.51
     throwback
    0.51
    颜值
    0.51
     prowad
    0.50
     fokus
    0.50
     moniker
    0.50
    POSITIVE LOGITS
     mellitus
    0.47
     prostitutes
    0.47
     imasmim
    0.45
     Cbd
    0.43
     rheumatism
    0.43
    দিগকে
    0.43
     Petersburg
    0.42
     robbers
    0.42
     prostitute
    0.42
     diabetes
    0.41
    Act Density 0.000%

    No Known Activations