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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perg
    -0.07
     anchor
    -0.07
     church
    -0.07
    iert
    -0.07
     '';
↵
    -0.06
     letech
    -0.06
    ']]↵
    -0.06
    鉄道
    -0.06
    importe
    -0.06
    stashop
    -0.06
    POSITIVE LOGITS
     guardian
    0.07
    Spin
    0.07
     (!
    0.07
     Badge
    0.07
     bosses
    0.06
     roast
    0.06
    (pointer
    0.06
     Гар
    0.06
    (in
    0.06
    BUS
    0.06
    Act Density 0.070%

    No Known Activations