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

    Neuronpedia

    INDEX
    Explanations

    intention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dba
    -0.07
     ours
    -0.07
    ambda
    -0.07
    _hierarchy
    -0.06
    Ele
    -0.06
     Lamb
    -0.06
    ้เป
    -0.06
    Allow
    -0.06
    émon
    -0.06
     Mak
    -0.06
    POSITIVE LOGITS
    ！！↵↵
    0.06
    卷
    0.06
     graduate
    0.06
     асп
    0.06
     unintention
    0.06
    ียง
    0.06
    레스
    0.06
    áveis
    0.06
    stations
    0.06
    （
    0.06
    Act Density 0.013%

    No Known Activations