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

    Neuronpedia

    INDEX
    Explanations

    Covering up incidents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Translated
    -0.08
     хоть
    -0.08
     Prep
    -0.07
     fair
    -0.07
     Kai
    -0.07
     Validate
    -0.07
    魔王
    -0.07
    打开了
    -0.06
    _money
    -0.06
    cesso
    -0.06
    POSITIVE LOGITS
    윕
    0.08
    รว
    0.07
    而非
    0.07
    𝗯
    0.07
    _rows
    0.07
    инг
    0.06
     Lecture
    0.06
    quiv
    0.06
    Asset
    0.06
    ὐ
    0.06
    Act Density 0.012%

    No Known Activations