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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    -blind
    -0.07
    感じる
    -0.07
    .Random
    -0.07
    ることができる
    -0.07
    \Base
    -0.07
    に入る
    -0.07
     사람이
    -0.06
    宴会
    -0.06
    "."
    -0.06
    ."/
    -0.06
    POSITIVE LOGITS
     Eaton
    0.08
    raham
    0.08
    _echo
    0.08
    岛
    0.07
     attachment
    0.07
     Ty
    0.07
     functionality
    0.07
    破损
    0.07
    尘
    0.07
    uploader
    0.07
    Act Density 0.016%

    No Known Activations