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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    混
    -0.07
    ยก
    -0.07
    前的
    -0.06
     �
    -0.06
     características
    -0.06
     ifad
    -0.06
    ailure
    -0.06
     uploaded
    -0.06
    -font
    -0.06
     도시
    -0.06
    POSITIVE LOGITS
    }`;↵
    0.06
    	mat
    0.06
     `;↵
    0.06
    (products
    0.06
     aust
    0.06
    timeout
    0.06
    ,ev
    0.05
     resultat
    0.05
     adapting
    0.05
     ниже
    0.05
    Act Density 0.024%

    No Known Activations