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

    Neuronpedia

    INDEX
    Explanations

    prepositions and articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Indie
    -0.10
    Premium
    -0.08
    Oi
    -0.08
    透露
    -0.07
     Premium
    -0.07
    owired
    -0.07
     платить
    -0.07
    好的
    -0.07
     محتر
    -0.07
     statues
    -0.07
    POSITIVE LOGITS
     importantly
    0.09
    その他
    0.09
     additionally
    0.08
     thereafter
    0.08
     furthermore
    0.08
     اینکه
    0.08
     sidoo
    0.08
     همچنین
    0.08
     sellele
    0.07
    går
    0.07
    Act Density 0.380%

    No Known Activations