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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _accounts
    -0.07
     isLoggedIn
    -0.07
    στρο
    -0.07
    retweeted
    -0.07
     есть
    -0.07
     proportions
    -0.07
    _provider
    -0.06
    .Green
    -0.06
    -blood
    -0.06
    pre
    -0.06
    POSITIVE LOGITS
    全球
    0.07
    …↵↵↵
    0.06
    OTP
    0.06
    (fname
    0.06
     dex
    0.06
    :")
    0.06
    대를
    0.06
    ("""
    0.06
     台
    0.06
    asket
    0.06
    Act Density 0.021%

    No Known Activations