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

    Neuronpedia

    INDEX
    Explanations

    legal codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ☣
    -0.07
    adders
    -0.06
    Ŕ
    -0.06
    .solution
    -0.06
    还真
    -0.06
    .assertTrue
    -0.06
    !!↵
    -0.06
     mom
    -0.06
     mẹ
    -0.06
     dú
    -0.06
    POSITIVE LOGITS
    �
    0.07
    ijk
    0.07
    开发建设
    0.07
     włas
    0.07
    _TRIGGER
    0.07
     occupy
    0.07
    Playlist
    0.07
    _rpc
    0.07
    _Handle
    0.07
     Audrey
    0.07
    Act Density 0.006%

    No Known Activations