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

    Neuronpedia

    INDEX
    Explanations

    numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     .:
    0.39
     согласно
    0.39
     사이에
    0.38
     }$
    0.36
     बगैर
    0.36
     machined
    0.36
     അവ
    0.36
     일부
    0.36
     tabulated
    0.35
    最后
    0.35
    POSITIVE LOGITS
    Lady
    0.37
    媜
    0.36
    ғы
    0.35
    Soul
    0.35
    👹
    0.35
     yaşanan
    0.35
    ȟ
    0.35
    READER
    0.34
    发展的
    0.33
    ढ़े
    0.33
    Act Density 0.005%

    No Known Activations