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

    Neuronpedia

    INDEX
    Explanations

    times/twice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Impl
    -0.07
     �
    -0.07
    _topics
    -0.07
    �
    -0.06
    .Handle
    -0.06
    能源
    -0.06
     사항
    -0.06
     Cont
    -0.06
    ництва
    -0.06
    CFG
    -0.06
    POSITIVE LOGITS
     inappropriate
    0.06
    Weapon
    0.06
    ृष
    0.06
     Queries
    0.06
    odiac
    0.06
    ingham
    0.06
     Doom
    0.06
    �
    0.06
     Mystic
    0.06
    спіль
    0.06
    Act Density 0.017%

    No Known Activations