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
     Games
    -0.07
     Sensors
    -0.07
     Paladin
    -0.07
    Proc
    -0.07
    rello
    -0.06
    otp
    -0.06
    XYZ
    -0.06
    awesome
    -0.06
    otate
    -0.06
    swagen
    -0.06
    POSITIVE LOGITS
     whose
    0.07
    ’s
    0.07
     theres
    0.07
     gallery
    0.07
    .Blocks
    0.07
     Valve
    0.06
    !')↵↵
    0.06
     виріш
    0.06
    whose
    0.06
    ulario
    0.06
    Act Density 0.077%

    No Known Activations