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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    झ
    -0.07
     tha
    -0.07
     widening
    -0.06
    ур
    -0.06
     freezer
    -0.06
    JR
    -0.06
    oration
    -0.06
    etsk
    -0.06
    HS
    -0.06
     öz
    -0.06
    POSITIVE LOGITS
    #{@
    0.07
    送料無料
    0.07
     Monkey
    0.07
     tekn
    0.07
    \Console
    0.07
    (coords
    0.06
     Hydra
    0.06
     portfolios
    0.06
    .classList
    0.06
    bral
    0.06
    Act Density 0.009%

    No Known Activations