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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jsonString
    -0.07
    उन
    -0.07
    акон
    -0.06
    	handler
    -0.06
     saç
    -0.06
     정확
    -0.06
     vaše
    -0.06
     دری
    -0.06
    住
    -0.06
    uman
    -0.06
    POSITIVE LOGITS
    帶
    0.06
    Bat
    0.06
     thể
    0.06
     日本
    0.06
    !'
    0.06
     ｜
    0.06
    
    0.06
    opolitan
    0.06
    ження
    0.06
    !"
    0.06
    Act Density 0.021%

    No Known Activations