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

    Neuronpedia

    INDEX
    Explanations

    ages and vulnerability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Improves
    0.41
     Transforms
    0.38
     Electroly
    0.38
     OSHA
    0.38
     SSSR
    0.37
     HDPE
    0.37
     Probably
    0.37
     Amendments
    0.37
     INCLUDING
    0.37
    ANTES
    0.37
    POSITIVE LOGITS
     vẫn
    0.45
    ⼀
    0.45
     senang
    0.45
     воспомина
    0.45
     isang
    0.44
     godt
    0.44
     bı
    0.44
     sesuatu
    0.43
     silenced
    0.43
     दमदार
    0.43
    Act Density 0.002%

    No Known Activations