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

    Neuronpedia

    INDEX
    Explanations

    rewriting code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    scopes
    -0.07
    _d
    -0.07
    岁
    -0.07
    歲
    -0.06
    -स
    -0.06
    ac
    -0.06
    濃
    -0.06
    -sur
    -0.06
     Bal
    -0.06
    	Toast
    -0.06
    POSITIVE LOGITS
    νω
    0.08
    那个
    0.07
     elaborate
    0.07
     ＞
    0.07
     awaken
    0.06
     Pedido
    0.06
    一样
    0.06
     richtig
    0.06
    WN
    0.06
    رخ
    0.06
    Act Density 0.010%

    No Known Activations