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

    Neuronpedia

    INDEX
    Explanations

    say "the ending -ization"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’↵
    -0.07
     assemblies
    -0.07
     hak
    -0.07
    泥
    -0.06
    Tpl
    -0.06
     besar
    -0.06
    Vehicle
    -0.06
     bonuses
    -0.06
    .inv
    -0.06
     Attempts
    -0.06
    POSITIVE LOGITS
    щё
    0.07
    etsy
    0.07
    crc
    0.06
    imachinery
    0.06
    umbled
    0.06
    .ASCII
    0.06
     Etsy
    0.06
    터
    0.06
    came
    0.06
     raw
    0.06
    Act Density 0.002%

    No Known Activations