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

    Neuronpedia

    INDEX
    Explanations

    research publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compiler
    -0.07
    後の
    -0.07
     Drama
    -0.07
    Global
    -0.06
    !!↵↵
    -0.06
     cards
    -0.06
     enumerated
    -0.06
    ấp
    -0.06
    good
    -0.06
     Separate
    -0.06
    POSITIVE LOGITS
     nuis
    0.07
     BTS
    0.06
    .JpaRepository
    0.06
    .contentMode
    0.06
     аб
    0.06
     cams
    0.06
     à
    0.05
     спів
    0.05
     hPa
    0.05
     imageNamed
    0.05
    Act Density 0.005%

    No Known Activations