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

    Neuronpedia

    INDEX
    Explanations

    Archangels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     במידה
    -0.08
    땃
    -0.07
    葵
    -0.07
    �
    -0.07
     playground
    -0.07
    ととも
    -0.07
    �
    -0.07
    ですよ
    -0.07
    新农村
    -0.07
     looked
    -0.07
    POSITIVE LOGITS
    Ḿ
    0.06
     solves
    0.06
    _scal
    0.06
     prophecy
    0.06
    ticker
    0.06
    指控
    0.06
    _j
    0.06
    anj
    0.06
     DOJ
    0.06
     clase
    0.06
    Act Density 0.019%

    No Known Activations